© 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. 9100
    Prev
    Next
    INDEX
    Explanations

    actors' names

    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
    $};
    2.99
    $}
    2.63
    he
    2.57
    te
    2.35
    (-\
    2.33
    otros
    2.32
    k
    2.27
    う
    2.24
     actualización
    2.23
     cerrada
    2.22
    POSITIVE LOGITS
    ن
    2.99
    ד
    2.76
    ities
    2.70
    ட்சத்திர
    2.43
    ި
    2.39
    𝑏
    2.38
    ли
    2.36
    
    2.34
    靼
    2.33
    ͹
    2.28
    Activations Density 0.022%

    No Known Activations