© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12357
    Prev
    Next
    INDEX
    Explanations

    words related to actions, movement, and file management, often in a programming context.

    oai_token-act-pair · gemini-2.0-flash

    say "it"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    awtextra
    -0.95
    UIControlState
    -0.76
    Vidite
    -0.73
     Theſe
    -0.72
    RenderAtEndOf
    -0.71
    adaptiveStyles
    -0.70
     THEM
    -0.67
    '}';
    -0.65
    them
    -0.65
     continúas
    -0.64
    POSITIVE LOGITS
     it
    1.88
     It
    1.08
    It
    0.96
    it
    0.91
     оно
    0.77
     that
    0.73
     它
    0.73
    它
    0.72
     this
    0.72
     the
    0.72
    Activations Density 7.917%

    No Known Activations