© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13052
    Prev
    Next
    INDEX
    Explanations

    words/phrases that are the start of words, are truncated, have non-alphanumeric characters right above it, have misspellings or other text artifacts

    oai_token-act-pair · gemini-2.0-flash

    technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    TintMode
    -0.57
     sacrament
    -0.50
     doInBackground
    -0.49
    ggers
    -0.49
    pet
    -0.49
    Servers
    -0.47
     Mont
    -0.47
    rollers
    -0.47
     pact
    -0.46
    WERS
    -0.46
    POSITIVE LOGITS
    MockMvc
    0.70
    enumii
    0.69
     CreateTagHelper
    0.65
    elts
    0.64
    
    0.62
    ConstraintMaker
    0.60
    enumi
    0.57
    tacts
    0.57
     quæ
    0.56
    MENAFN
    0.55
    Activations Density 4.765%

    No Known Activations