© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4211
    Prev
    Next
    INDEX
    Explanations

    text followed by a number or a number followed by text

    oai_token-act-pair · gemini-2.0-flash

    say "an example"

    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
     an
    -0.92
     app
    -0.62
     ar
    -0.60
     officer
    -0.59
     artist
    -0.59
     army
    -0.59
     arch
    -0.59
     element
    -0.58
     energy
    -0.58
     op
    -0.57
    POSITIVE LOGITS
    tagHelperRunner
    1.03
    RenderAtEndOf
    0.75
    WithIOException
    0.75
    ConstraintMaker
    0.73
    InjectAttribute
    0.71
    mobileqq
    0.69
     متعلقه
    0.68
    دانشنامهٔ
    0.68
     تضيفلها
    0.67
    "]();
    0.67
    Activations Density 1.058%

    No Known Activations