© 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. 7498
    Prev
    Next
    INDEX
    Explanations

    而 + verb/adjective

    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
    Tapi
    1.06
     alkene
    1.03
     चलकर
    0.99
    욱
    0.99
    usescu
    0.95
     pathname
    0.95
    orghini
    0.94
     alken
    0.93
     imshow
    0.88
     leto
    0.88
    POSITIVE LOGITS
     appealing
    1.04
     effettu
    0.95
    Câu
    0.93
     बंद
    0.89
    ه
    0.89
     awhile
    0.89
     گذا
    0.87
    identical
    0.85
     dimin
    0.85
     megfelel
    0.84
    Activations Density 0.002%

    No Known Activations