© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34772
    Prev
    Next
    INDEX
    Explanations

    5px

    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_31_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
     oligonucle
    0.37
    вак
    0.37
    FlightID
    0.36
    ジン
    0.34
    $.}
    0.34
     Kurulu
    0.33
    妝
    0.33
    കു
    0.33
    <0xB8>
    0.33
    ólico
    0.33
    POSITIVE LOGITS
     Trim
    0.41
     Kahn
    0.37
     reputation
    0.36
     Mohamed
    0.36
     uni
    0.35
     Pric
    0.35
     More
    0.35
     treat
    0.34
     Hund
    0.34
     तरह
    0.34
    Activations Density 0.002%

    No Known Activations