© 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. 133915
    Prev
    Next
    INDEX
    Explanations

    social engineering attack tactic

    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
    ,
    1.03
     a
    1.02
    ↵
    0.95
    on
    0.88
    }$
    0.87
    m
    0.86
    ב
    0.85
    Page
    0.83
    Type
    0.80
    ina
    0.79
    POSITIVE LOGITS
     ತುಂಬಾ
    0.84
    ﻧ
    0.84
    ﺃ
    0.73
    ですが
    0.71
     Sauv
    0.70
     Seit
    0.70
     Mahatma
    0.68
    ﺗ
    0.68
    ાર્
    0.68
     cuốn
    0.68
    Activations Density 0.000%

    No Known Activations