© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38168
    Prev
    Next
    INDEX
    Explanations

    breitcordhose

    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_3_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
    ה
    1.09
    م
    0.99
    ،
    0.98
    ט
    0.93
    ত
    0.93
    گ
    0.90
    ގ
    0.84
    त
    0.83
    お客
    0.82
    ۵
    0.82
    POSITIVE LOGITS
     a
    0.76
    o
    0.74
     e
    0.72
    VB
    0.71
    ement
    0.71
    ic
    0.70
    ü
    0.70
    ia
    0.69
    }
    0.68
    í
    0.68
    Activations Density 0.001%

    No Known Activations