© 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. 162906
    Prev
    Next
    INDEX
    Explanations

    police and law

    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
    晠
    0.44
     Trabalho
    0.38
    ameron
    0.38
     TAD
    0.38
    ählten
    0.38
     SCSI
    0.37
    ajero
    0.37
    áž
    0.36
    𝔞
    0.36
     painfully
    0.36
    POSITIVE LOGITS
    pall
    0.42
    πτ
    0.41
    Police
    0.41
    Crown
    0.41
     полицей
    0.39
     پولیس
    0.38
    Susp
    0.38
     policemen
    0.37
     pall
    0.37
    jog
    0.37
    Activations Density 0.015%

    No Known Activations