© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111720
    Prev
    Next
    INDEX
    Explanations

    hyponym / ph + osis

    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_2_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
    i
    2.05
    a
    1.91
    ي
    1.90
    iin
    1.87
    el
    1.63
    in
    1.56
    ে
    1.51
    iul
    1.49
    ۹
    1.41
    ין
    1.38
    POSITIVE LOGITS
    .
    1.45
    ,
    1.27
    1
    1.23
    _.
    1.19
    _
    1.15
    R
    1.15
    .`
    1.12
    ().
    1.03
    .$
    1.02
    G
    0.97
    Activations Density 0.000%

    No Known Activations