© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78492
    Prev
    Next
    INDEX
    Explanations

    code and logs

    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_53_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
    Л
    0.48
     Лон
    0.47
    ลอด
    0.46
     Λ
    0.46
     Ло
    0.45
     LCS
    0.44
     LI
    0.43
    ло
    0.41
     ල
    0.41
    ോ
    0.41
    POSITIVE LOGITS
    ษย์
    0.40
     hag
    0.40
    kable
    0.37
     Boogie
    0.37
    quint
    0.37
     sierpnia
    0.37
     Där
    0.36
    hag
    0.36
    κες
    0.36
    Village
    0.35
    Activations Density 0.007%

    No Known Activations