© 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. 232191
    Prev
    Next
    INDEX
    Explanations

    OH followed by exclamation or title

    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
    ang
    1.03
    un
    0.88
    ↵↵
    0.80
     DOI
    0.80
    াই
    0.79
    ab
    0.76
    á
    0.73
     CREE
    0.71
    é
    0.71
     fireplace
    0.71
    POSITIVE LOGITS
    전
    1.14
    자
    1.05
     wichtiger
    0.99
    Д
    0.96
    いた
    0.95
    hz
    0.95
    기
    0.94
    Мо
    0.93
    미
    0.93
    hmm
    0.92
    Activations Density 0.000%

    No Known Activations