© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12105
    Prev
    Next
    INDEX
    Explanations

    comments and notes

    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_40_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
    frog
    0.39
    istro
    0.38
    줄
    0.38
     LINES
    0.36
     lij
    0.34
    LINES
    0.34
    ifai
    0.34
     Fade
    0.33
    
    0.33
     Mull
    0.33
    POSITIVE LOGITS
     note
    1.91
     Note
    1.63
    note
    1.60
    Note
    1.58
     notes
    1.52
     NOTE
    1.48
    NOTE
    1.38
    注
    1.38
     nota
    1.37
     नोट
    1.35
    Activations Density 0.023%

    No Known Activations