© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12955
    Prev
    Next
    INDEX
    Explanations

    dollar signs and numbers, possibly identifying numerical data or currency values

    oai_token-act-pair · gemini-2.0-flash

    1

    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
    enterOuterAlt
    -0.73
    <bos>
    -0.57
     x
    -0.50
    zeka
    -0.44
    dymyr
    -0.42
    latego
    -0.42
     resourceCulture
    -0.41
    exitRule
    -0.41
     enca
    -0.41
    ChildScrollView
    -0.41
    POSITIVE LOGITS
    providedIn
    0.68
    0
    0.61
     argint
    0.61
    ISupport
    0.60
    مصادر
    0.59
     переписи
    0.59
     vertes
    0.59
    tadır
    0.59
     Juifs
    0.59
     onlyOwner
    0.58
    Activations Density 8.173%

    No Known Activations