© 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. 7310
    Prev
    Next
    INDEX
    Explanations

    to yourself, your, the, me

    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
    at
    1.31
     вот
    1.23
     visione
    1.19
     dụng
    1.18
     tenha
    1.17
    с
    1.15
    uin
    1.13
    ap
    1.11
    از
    1.07
    <0x80>
    1.07
    POSITIVE LOGITS
     subscript
    1.32
    ם
    1.25
     hinged
    1.24
     caveat
    1.20
     truncated
    1.14
    ァ
    1.09
     ishlab
    1.09
    Rpc
    1.06
     privileged
    1.06
     суда
    1.05
    Activations Density 0.074%

    No Known Activations