© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9609
    Prev
    Next
    INDEX
    Explanations

    status quo or characteristics

    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_13_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
     К
    0.15
     Ж
    0.15
     Cameroon
    0.13
    КА
    0.13
    "。
    0.13
    жима
    0.13
    Ｋ
    0.13
     जीबी
    0.13
     त
    0.13
    罂
    0.12
    POSITIVE LOGITS
    Welt
    0.15
     spesso
    0.14
    Male
    0.14
    iac
    0.14
    sample
    0.14
    Werk
    0.14
    Define
    0.14
    i
    0.14
    tudo
    0.13
    Discrete
    0.13
    Activations Density 0.013%

    No Known Activations