© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9921
    Prev
    Next
    INDEX
    Explanations

    code snippets in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    arquivo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    findpost
    -0.79
     GenerationType
    -0.73
    UnusedPrivate
    -0.53
     vérit
    -0.50
     paździer
    -0.46
     commission
    -0.46
    reps
    -0.46
     backup
    -0.45
    inheritDoc
    -0.44
    gione
    -0.44
    POSITIVE LOGITS
    PerformLayout
    0.67
     handleMessage
    0.56
    ClientSize
    0.55
     Ngb
    0.55
    ]-'
    0.54
    putin
    0.52
    ResumeLayout
    0.52
    tabolism
    0.51
     inhale
    0.50
     Wikispecies
    0.49
    Activations Density 1.352%

    No Known Activations