© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60924
    Prev
    Next
    INDEX
    Explanations

    hesitate to

    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_11_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
    ᱐
    0.71
     probative
    0.66
    ված
    0.65
     зар
    0.62
     notifies
    0.62
    вобо
    0.61
    крыть
    0.61
    ப்படுத்தி
    0.61
    ина
    0.61
    ента
    0.60
    POSITIVE LOGITS
    सी
    0.63
    \
    0.61
    0.59
    o
    0.57
    Від
    0.53
    مس
    0.53
    مش
    0.52
    ↵
    0.51
     Pen
    0.51
     للص
    0.51
    Activations Density 0.001%

    No Known Activations