© 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. 7716
    Prev
    Next
    INDEX
    Explanations

    family history

    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
    े
    2.23
    ে
    2.17
    ו
    2.08
    ه
    2.06
    o
    2.06
    та
    1.93
    า
    1.90
    athy
    1.90
    ο
    1.84
    е
    1.79
    POSITIVE LOGITS
    or
    2.34
    ぞれ
    2.23
     oscilloscope
    2.14
     tooltip
    2.07
    ſe
    2.02
    TES
    2.02
     aquifer
    2.00
    ˹
    1.98
     accessToken
    1.95
     dermal
    1.95
    Activations Density 0.006%

    No Known Activations