© 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. 5669
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to importance, planning, and management

    oai_token-act-pair · gemini-2.0-flash

    important

    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
    tagext
    -0.58
    ]^{-
    -0.52
    Bund
    -0.52
    quels
    -0.50
     kasarigan
    -0.50
    =$((
    -0.50
    stdc
    -0.49
    [::-
    -0.48
    xito
    -0.48
    CardBody
    -0.48
    POSITIVE LOGITS
     for
    0.90
     that
    0.87
     to
    0.67
     then
    0.59
     from
    0.58
     FOR
    0.56
    LabelTagHelper
    0.55
    —
    0.53
    ScopeManager
    0.53
    SqlClient
    0.51
    Activations Density 14.782%

    No Known Activations