© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34388
    Prev
    Next
    INDEX
    Explanations

    following up

    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_3_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
    ő
    0.90
    做
    0.74
     начиная
    0.74
    ější
    0.67
    어
    0.66
    1
    0.65
    ící
    0.63
    <0x91>
    0.61
     осо
    0.61
    <0xBE>
    0.60
    POSITIVE LOGITS
    ICK
    0.82
     Purse
    0.74
    ATCH
    0.73
    ج
    0.69
    OWN
    0.69
    ोरेशन
    0.69
    لین
    0.69
    ص
    0.68
     Agricult
    0.67
     Settlements
    0.67
    Activations Density 0.001%

    No Known Activations