© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195130
    Prev
    Next
    INDEX
    Explanations

    after greetings or questions

    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_9_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
     gathered
    0.61
    ose
    0.52
     as
    0.52
    esk
    0.52
     girlfriend
    0.50
     cultured
    0.50
     â
    0.49
     Спорт
    0.49
     и
    0.49
     wildcard
    0.49
    POSITIVE LOGITS
    왼
    0.55
    Bug
    0.53
    ัล
    0.52
    Resultado
    0.49
    Verlag
    0.48
    Après
    0.48
    υσ
    0.47
    Projeto
    0.47
    MDET
    0.46
    Dopo
    0.46
    Activations Density 0.000%

    No Known Activations