© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151102
    Prev
    Next
    INDEX
    Explanations

    End of comment

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Bat
    0.43
    --
    0.43
    Sag
    0.42
    Owen
    0.42
    Function
    0.41
    Le
    0.40
    Stephen
    0.40
    St
    0.40
    Leg
    0.40
    Legal
    0.38
    POSITIVE LOGITS
     public
    0.57
    public
    0.56
     Public
    0.54
     공
    0.48
     सार्वजनिक
    0.47
    ublic
    0.46
     series
    0.45
     публи
    0.45
     ribbons
    0.45
     öffentliche
    0.44
    Activations Density 0.001%

    No Known Activations