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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 502
    Prev
    Next
    INDEX
    Explanations

    words related to machine learning and statistical analysis

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    GraphicsUnit
    -0.62
    TagMode
    -0.61
     دیکھیے
    -0.60
     nahilalakip
    -0.58
    tahui
    -0.58
     indisponible
    -0.57
    writeField
    -0.56
    UserScript
    -0.55
    ökk
    -0.55
     Unavailable
    -0.53
    POSITIVE LOGITS
     reason
    0.68
     reafon
    0.65
    Reason
    0.57
    UnsafeEnabled
    0.56
    reason
    0.56
     reasons
    0.52
    DockStyle
    0.52
     ragione
    0.48
     Reason
    0.48
    </tfoot>
    0.47
    Activations Density 5.621%

    No Known Activations