© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126677
    Prev
    Next
    INDEX
    Explanations

    dosage amounts in milligrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     الترك
    0.39
    AAF
    0.38
    პ
    0.38
     ascertained
    0.37
     kurt
    0.37
    میل
    0.37
     bel
    0.36
    ぎ
    0.36
     erk
    0.35
    œuvre
    0.35
    POSITIVE LOGITS
     Sanitary
    0.41
    櫥
    0.40
    卫生
    0.40
     sanitary
    0.39
     GDP
    0.38
    lander
    0.36
    Sight
    0.36
    აწილ
    0.36
    ivac
    0.36
     vess
    0.35
    Activations Density 0.002%

    No Known Activations