© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25701
    Prev
    Next
    INDEX
    Explanations

    Long integer ids

    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_10_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
    ز
    0.65
    Weak
    0.61
    belly
    0.61
    բ
    0.58
    Ᏹ
    0.57
    them
    0.56
    л
    0.55
    咘
    0.55
    Been
    0.54
    𝐠
    0.54
    POSITIVE LOGITS
    omba
    0.73
    ud
    0.68
     শুধুমাত্র
    0.68
     हार्मोन
    0.67
     that
    0.66
    ivi
    0.63
     पासवर्ड
    0.62
     هست
    0.62
    uda
    0.61
     }}=\
    0.61
    Activations Density 0.001%

    No Known Activations