© 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. 15242
    Prev
    Next
    INDEX
    Explanations

    words related to audio/visual recordings used as evidence in a crime.

    oai_token-act-pair · gemini-2.0-flash

    Video and Audio Recording

    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
    **
    -0.45
    ...
    -0.43
    <strong>
    -0.41
     kepercayaan
    -0.41
     an
    -0.40
    <eos>
    -0.39
    '
    -0.39
    信
    -0.38
    ，
    -0.38
    :
    -0.38
    POSITIVE LOGITS
    IntoConstraints
    0.96
    protoimpl
    0.94
    rrggbb
    0.86
     <<<<<<<<<<<<<<
    0.84
    AndEndTag
    0.82
    PageFactory
    0.81
    \"");
    0.81
    verwijspagina
    0.81
    featureID
    0.81
    PerformLayout
    0.79
    Activations Density 1.609%

    No Known Activations