© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216561
    Prev
    Next
    INDEX
    Explanations

    party affiliation and history

    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_31_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
     Alf
    0.37
     council
    0.33
     особы
    0.33
     alf
    0.32
     Ros
    0.32
    oten
    0.32
     l
    0.32
     unorthodox
    0.31
     অতীত
    0.31
    box
    0.31
    POSITIVE LOGITS
    댐
    0.37
    Cidade
    0.35
    控件
    0.35
    шите
    0.34
     territoriale
    0.34
     Aleksandar
    0.34
    oscale
    0.34
    )}_
    0.33
    굴
    0.33
    蔘
    0.33
    Activations Density 0.002%

    No Known Activations