© 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. 85680
    Prev
    Next
    INDEX
    Explanations

    emojis and specific characters

    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
     to
    0.88
     in
    0.81
     of
    0.73
    ך
    0.73
     interfacial
    0.68
    在
    0.67
    보
    0.67
    ने
    0.63
     homogenization
    0.63
    ست
    0.63
    POSITIVE LOGITS
    is
    0.77
    ти
    0.67
    ua
    0.65
     யா
    0.64
    oare
    0.64
    uds
    0.64
    на
    0.61
    á
    0.61
    ay
    0.60
    ungsl
    0.59
    Activations Density 0.000%

    No Known Activations