© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8950
    Prev
    Next
    INDEX
    Explanations

    client objects, database clients

    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
    此之外
    2.46
    тип
    2.39
    тность
    2.35
    ように
    2.35
    zelfde
    2.33
     stip
    2.33
    𝑦
    2.30
     nomina
    2.27
     vyb
    2.21
    nivers
    2.20
    POSITIVE LOGITS
    Ш
    2.26
    f
    2.18
     சேர்ந்து
    2.16
    spe
    2.07
    ANDE
    2.05
    办法
    2.04
     Zr
    2.03
    ier
    2.01
    cstdlib
    1.99
     Beratung
    1.98
    Activations Density 0.003%

    No Known Activations