© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204954
    Prev
    Next
    INDEX
    Explanations

    new

    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_37_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
     בז
    0.41
     new
    0.40
    rug
    0.38
    new
    0.38
    É
    0.37
    LIST
    0.36
     newest
    0.36
     popul
    0.36
     basil
    0.36
     newsp
    0.35
    POSITIVE LOGITS
    逭
    0.38
     Succeed
    0.37
    的正
    0.37
    க்கத்தில்
    0.36
     ვი
    0.36
     Callback
    0.35
     ভাত
    0.35
     హీరోయి
    0.35
    允
    0.35
    VIDOR
    0.35
    Activations Density 0.000%

    No Known Activations