© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1953
    Prev
    Next
    INDEX
    Explanations

    language surrounding numerical values, including time, dates, and other quantities

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Six
    -2.25
    Six
    -2.25
    Eight
    -2.22
     Eight
    -2.20
    Nine
    -2.19
    Five
    -2.17
     Nine
    -2.17
     Seven
    -2.17
    Seven
    -2.17
     Five
    -2.14
    POSITIVE LOGITS
    DockStyle
    0.65
     '\\;'
    0.65
    Geplaatst
    0.60
    ArgsConstructor
    0.60
    клопе
    0.59
    Portail
    0.59
    Obrázky
    0.56
    <bos>
    0.51
    AutoScaleMode
    0.51
    abinieri
    0.51
    Activations Density 5.449%

    No Known Activations