© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150181
    Prev
    Next
    INDEX
    Explanations

    .

    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_60_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
     pushing
    2.95
     push
    2.89
     Push
    2.86
    Push
    2.78
    推
    2.73
     pushed
    2.70
     pushes
    2.70
    push
    2.55
     pusher
    2.41
    PUSH
    2.30
    POSITIVE LOGITS
     P
    0.63
    П
    0.41
     П
    0.41
    P
    0.38
     प्रताप
    0.37
    Ｐ
    0.37
    부가
    0.36
    getP
    0.34
    ാവ്
    0.34
     Pratap
    0.34
    Activations Density 0.007%

    No Known Activations