© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5178
    Prev
    Next
    INDEX
    Explanations

    scientific or technical discourse with keywords such as "parameters", "important", "measured", and "this"

    oai_token-act-pair · gemini-2.0-flash

    measured characteristics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    StoryboardSegue
    -1.03
    rungsseite
    -0.87
    TagMode
    -0.85
    verwijspagina
    -0.85
     CreateTagHelper
    -0.83
     Reverso
    -0.82
     snippetHide
    -0.78
     disambiguazione
    -0.77
     defaultstate
    -0.75
    providedIn
    -0.73
    POSITIVE LOGITS
     factors
    0.78
     parameters
    0.69
    要素
    0.66
     aspects
    0.66
     Factors
    0.63
     aspectos
    0.62
     factores
    0.61
    factors
    0.60
     factor
    0.60
     aspecto
    0.59
    Activations Density 2.411%

    No Known Activations