© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130563
    Prev
    Next
    INDEX
    Explanations

    hexagonal

    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
     a
    0.96
    0.95
    l
    0.93
    \
    0.93
    ge
    0.87
    “
    0.82
    nd
    0.81
    dig
    0.81
    ductors
    0.79
    da
    0.78
    POSITIVE LOGITS
    is
    1.48
    س
    1.46
    ला
    1.31
    ри
    1.29
    на
    1.26
    ir
    1.25
    ன்
    1.23
    ه
    1.20
    น
    1.20
    نا
    1.13
    Activations Density 0.000%

    No Known Activations