© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205501
    Prev
    Next
    INDEX
    Explanations

    It's great you

    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_6_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
    ד
    0.75
    ного
    0.74
    fueled
    0.74
    нов
    0.73
    دين
    0.73
    numerical
    0.73
    اد
    0.73
    好好
    0.73
    foration
    0.71
    مون
    0.71
    POSITIVE LOGITS
    \
    1.12
     I
    0.92
     Andhra
    0.91
    자
    0.84
     Sodium
    0.84
     Kenya
    0.83
     Aspergillus
    0.80
     Olympics
    0.80
     सभी
    0.78
     ahi
    0.78
    Activations Density 0.005%

    No Known Activations