© 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. 9174
    Prev
    Next
    INDEX
    Explanations

    small, adjective descriptions

    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
    Negative Logits
    <0x80>
    0.94
    в
    0.93
    ]})
    0.90
    า
    0.88
    Ľ
    0.88
     atât
    0.86
    📲
    0.86
    "$
    0.84
    𝘆
    0.83
     embold
    0.83
    POSITIVE LOGITS
    orous
    0.76
     plumes
    0.76
    ы
    0.73
    liest
    0.73
    ።
    0.73
    isolate
    0.72
    NP
    0.71
     serviceable
    0.70
    izing
    0.70
    M
    0.70
    Activations Density 0.296%

    No Known Activations