© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130166
    Prev
    Next
    INDEX
    Explanations

    startup ideas

    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_6_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
    0
    0.98
    ate
    0.71
     was
    0.71
    ;
    0.68
    0.66
    and
    0.65
    ola
    0.65
    ita
    0.64
    elle
    0.64
    anda
    0.63
    POSITIVE LOGITS
    만
    0.67
    Ꮈ
    0.63
    ін
    0.62
    하여
    0.59
     totalité
    0.58
    त
    0.58
    ل
    0.57
    ל
    0.56
    ᒐ
    0.55
    ᓲ
    0.55
    Activations Density 0.003%

    No Known Activations