© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89407
    Prev
    Next
    INDEX
    Explanations

    despondent, despotic, desensitize

    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
    ل
    1.09
    و
    0.99
    ه
    0.97
    B
    0.91
    س
    0.78
    K
    0.78
    V
    0.77
    ва
    0.77
    S
    0.77
    ча
    0.77
    POSITIVE LOGITS
    the
    0.88
    ten
    0.75
    ta
    0.74
    ti
    0.70
    do
    0.69
    ty
    0.67
    der
    0.66
    .
    0.66
     SQLAlchemy
    0.64
    ።
    0.64
    Activations Density 0.000%

    No Known Activations