© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106803
    Prev
    Next
    INDEX
    Explanations

    as many reps as possible

    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_1_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
    er
    1.21
    ан
    1.04
    ad
    0.98
    ana
    0.96
    iv
    0.96
    ist
    0.93
    р
    0.93
    ge
    0.93
    ॉन
    0.93
    OL
    0.89
    POSITIVE LOGITS
    ת
    1.58
    '
    1.56
    ل
    1.53
    ל
    1.48
     to
    1.34
    தி
    1.31
    ק
    1.31
    ን
    1.30
    ن
    1.27
     with
    1.23
    Activations Density 0.000%

    No Known Activations