© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80349
    Prev
    Next
    INDEX
    Explanations

    exploring different areas

    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_31_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
     способом
    0.40
    Ｖ
    0.39
    RatingDiff
    0.34
    iesis
    0.34
    gcc
    0.34
     sphincter
    0.34
     ovulation
    0.33
    谢
    0.33
    пами
    0.33
     Cenomanian
    0.32
    POSITIVE LOGITS
     culinary
    0.40
     aquatic
    0.40
     automotive
    0.38
     inver
    0.38
     intermolecular
    0.37
    inki
    0.37
     heavenly
    0.37
     kinemat
    0.36
     relating
    0.36
     woods
    0.36
    Activations Density 0.104%

    No Known Activations