© 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. 126913
    Prev
    Next
    INDEX
    Explanations

    makes a sound

    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
    řed
    0.84
    <0x0D>
    0.84
    مرين
    0.82
    ம
    0.82
    áculos
    0.80
    的
    0.79
     chino
    0.77
    不
    0.77
    মারের
    0.75
     čís
    0.75
    POSITIVE LOGITS
     can
    1.05
     I
    0.91
     be
    0.86
    ก
    0.84
    ic
    0.82
    ї
    0.80
    der
    0.77
    ly
    0.77
    ها
    0.77
    ות
    0.76
    Activations Density 0.000%

    No Known Activations