© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75823
    Prev
    Next
    INDEX
    Explanations

    job type / employment type

    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
    COC
    0.44
    鞄
    0.40
    SIP
    0.39
    和服务
    0.38
     شاعری
    0.38
    ύν
    0.37
    สร
    0.36
    繭
    0.36
    lettes
    0.36
    NAL
    0.35
    POSITIVE LOGITS
    General
    0.39
     General
    0.39
     Bernardo
    0.38
     Oppo
    0.37
     ótimo
    0.37
     Rafael
    0.37
     Hughes
    0.37
    vet
    0.36
    ুপ
    0.36
     tern
    0.36
    Activations Density 0.000%

    No Known Activations