© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97927
    Prev
    Next
    INDEX
    Explanations

    meth" followed by refusal

    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_14_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
    mallow
    0.53
    ando
    0.52
    osh
    0.52
     Osman
    0.51
    e
    0.51
    rainer
    0.50
    irmingham
    0.49
     kubb
    0.49
    umb
    0.48
    akespeare
    0.48
    POSITIVE LOGITS
    异常
    0.54
     abnormal
    0.50
     uner
    0.47
     correlated
    0.46
     abnormalities
    0.45
    異常
    0.45
    咥
    0.45
     ellipt
    0.45
    ج
    0.45
     permutations
    0.44
    Activations Density 0.003%

    No Known Activations