© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14346
    Prev
    Next
    INDEX
    Explanations

    words associated with hair, particularly in a forensic context.

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to hair treatment and cosmetology

    np_token-act-pair-logits · gpt-4o-mini

    code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     communism
    -0.47
     Communism
    -0.45
     comunista
    -0.45
     fekete
    -0.43
    locationManager
    -0.42
    Fordítás
    -0.42
    rubin
    -0.42
     peintre
    -0.41
    디어
    -0.41
    üksek
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    0.90
    RenderAtEndOf
    0.85
    StoryboardSegue
    0.82
     lenker
    0.81
    makeConstraints
    0.79
    EndContext
    0.75
    InjectAttribute
    0.75
     متعلقه
    0.74
    ConstraintMaker
    0.73
    principalTable
    0.72
    Activations Density 5.515%

    No Known Activations