© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34591
    Prev
    Next
    INDEX
    Explanations

    emphasis and warnings

    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_7_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
    am
    0.90
    odikwa
    0.87
    amı
    0.87
    行う
    0.83
    Ꮂ
    0.82
    ろし
    0.80
    า
    0.79
    itipi
    0.79
    눴
    0.79
    amız
    0.78
    POSITIVE LOGITS
     the
    0.93
     will
    0.93
    I
    0.92
    ফ
    0.90
     as
    0.89
    2
    0.88
     wird
    0.87
     are
    0.86
     le
    0.86
     el
    0.85
    Activations Density 0.056%

    No Known Activations