© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12944
    Prev
    Next
    INDEX
    Explanations

    occurrences of articles followed by descriptions of things, locations, or qualities.

    oai_token-act-pair · gemini-2.0-flash

    colors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    LookAnd
    -1.09
    InputBorder
    -0.56
    MethodManager
    -0.56
    IntoConstraints
    -0.54
    Clik
    -0.54
     HasFactory
    -0.53
    GraphicsUnit
    -0.53
     Мексичка
    -0.52
    addPreferredGap
    -0.52
    moveToFirst
    -0.50
    POSITIVE LOGITS
     red
    2.27
     blue
    2.25
     black
    2.17
     green
    2.11
     grey
    2.02
     gray
    2.00
     white
    1.96
     yellow
    1.95
     brown
    1.93
    blue
    1.90
    Activations Density 3.589%

    No Known Activations