© 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. 8985
    Prev
    Next
    INDEX
    Explanations

    ad to knead

    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
     mouths
    2.94
    le
    2.93
     searchable
    2.67
    ında
    2.67
     genders
    2.59
    ]),
    2.58
     परसेंट
    2.56
     перемо
    2.54
    CTIONS
    2.50
     brushed
    2.50
    POSITIVE LOGITS
    𝙧
    2.76
    та
    2.69
    ный
    2.63
    ير
    2.59
    ྱི་
    2.57
    ｆ
    2.41
    un
    2.35
    ц
    2.34
    に必要な
    2.33
    ניים
    2.29
    Activations Density 0.003%

    No Known Activations