© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1465
    Prev
    Next
    INDEX
    Explanations

    chunks of code

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · 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
     TextAppearance
    -0.36
    ThroughAttribute
    -0.35
    providedIn
    -0.34
    ní
    -0.33
    othe
    -0.30
    eding
    -0.30
    zzar
    -0.29
    `,`
    -0.29
    ',\
    -0.29
     Италијани
    -0.29
    POSITIVE LOGITS
    inderella
    0.84
    enumii
    0.71
     larmes
    0.71
    //
    0.70
     magique
    0.68
    brigens
    0.67
    öszi
    0.67
    quelize
    0.66
     religieuses
    0.66
     nemlig
    0.66
    Activations Density 2.035%

    No Known Activations