© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116457
    Prev
    Next
    INDEX
    Explanations

    refusal and `!--`

    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_27_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
     Estimates
    0.35
     estimations
    0.33
    iol
    0.31
     Marcelo
    0.30
     PICTOGRAM
    0.30
     $\$
    0.29
     estimates
    0.29
    見積
    0.28
     incluida
    0.28
    estimates
    0.28
    POSITIVE LOGITS
    ゑ
    0.33
    htë
    0.31
     originates
    0.30
     originated
    0.30
     zároveň
    0.30
     dope
    0.29
    也有
    0.28
    에서도
    0.28
    先把
    0.28
    karma
    0.28
    Activations Density 0.001%

    No Known Activations