© 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. 9144
    Prev
    Next
    INDEX
    Explanations

    South Park and Butler

    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
    ри
    1.97
     aantal
    1.92
    करण
    1.87
    ণ
    1.86
    или
    1.84
    ş
    1.81
    ㅀ
    1.80
     auxquels
    1.80
     imperfection
    1.80
    ції
    1.80
    POSITIVE LOGITS
    ravi
    2.13
    lagen
    2.04
    ности
    2.02
    ności
    1.91
    glColor
    1.91
    specifiedByURL
    1.89
     conductance
    1.88
    腺
    1.88
    originalname
    1.87
    pressed
    1.86
    Activations Density 0.005%

    No Known Activations