© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28265
    Prev
    Next
    INDEX
    Explanations

    Italian crime and locations

    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_40_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
    Separator
    0.44
    SEX
    0.43
     breathing
    0.43
    ḵ
    0.38
    性
    0.37
     हार्म
    0.37
    舗
    0.36
    opoe
    0.36
     சினி
    0.35
    __":
    0.35
    POSITIVE LOGITS
     mafia
    0.47
     Local
    0.46
     italien
    0.44
     Mafia
    0.43
     Venice
    0.42
     mayors
    0.42
    Italy
    0.41
     स्मिथ
    0.40
    Local
    0.40
     კან
    0.39
    Activations Density 0.000%

    No Known Activations