© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3656
    Prev
    Next
    INDEX
    Explanations

    colons, single hyphens, multi-character strings containing digits, periods, and minus signs, substrings surrounded by asterisks and backslashes and references to lines of code

    oai_token-act-pair · gemini-2.0-flash

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    rungsseite
    -0.53
     Hers
    -0.50
    RenderAtEndOf
    -0.48
    yanto
    -0.48
    tabular
    -0.45
    σία
    -0.45
    Suffix
    -0.44
    তথ্যসূত্র
    -0.43
     disambiguazione
    -0.43
    expandindo
    -0.42
    POSITIVE LOGITS
    BeginContext
    0.65
     ویکی‌پدیا
    0.63
    requestCode
    0.60
    fjspx
    0.59
     requestCode
    0.57
     QtGui
    0.57
     bParam
    0.56
    COUVER
    0.56
     nargin
    0.56
    InjectAttribute
    0.56
    Activations Density 1.707%

    No Known Activations