© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8228
    Prev
    Next
    INDEX
    Explanations

    pull-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    й
    2.95
    er
    2.75
    ER
    2.31
    <%=
    2.29
     vicinity
    2.28
    וכ
    2.20
    ()]
    2.14
    ation
    2.14
     Pasteur
    2.12
    nění
    2.12
    POSITIVE LOGITS
    sü
    2.23
     steep
    2.20
    hā
    2.20
    ست
    2.17
    𝕟
    2.15
     znan
    2.15
    на
    2.11
    𝕣
    2.09
    s
    2.07
    teste
    2.06
    Activations Density 0.042%

    No Known Activations