© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205530
    Prev
    Next
    INDEX
    Explanations

    legal professional

    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_6_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
    were
    0.76
    extremely
    0.73
    3
    0.72
    ind
    0.71
    injury
    0.70
    ill
    0.68
    ın
    0.68
    cribed
    0.68
    erving
    0.68
    int
    0.67
    POSITIVE LOGITS
    ى
    0.73
     was
    0.65
    ਰ
    0.65
     léka
    0.64
    at
    0.63
     is
    0.63
    лся
    0.63
    ↵
    0.62
     poč
    0.62
    บ
    0.62
    Activations Density 0.000%

    No Known Activations