© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104684
    Prev
    Next
    INDEX
    Explanations

    instructing use of vulgar content

    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_1_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
     в
    1.32
    ки
    1.31
     may
    1.26
     від
    1.23
     were
    1.20
     współprac
    1.19
     be
    1.17
     де
    1.17
     с
    1.16
     כ
    1.16
    POSITIVE LOGITS
    an
    1.60
    ان
    1.46
    g
    1.31
    j
    1.28
    ing
    1.24
    ch
    1.24
    in
    1.23
    r
    1.14
    al
    1.13
    t
    1.03
    Activations Density 0.001%

    No Known Activations