© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79445
    Prev
    Next
    INDEX
    Explanations

    journey

    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_0_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
    an
    2.23
    t
    2.22
    are
    1.76
    ۔
    1.67
     on
    1.66
    i
    1.64
    。
    1.62
    R
    1.60
    ar
    1.59
    un
    1.56
    POSITIVE LOGITS
    ಾರೆ
    1.25
    ;}
    1.20
    }">
    1.19
    その他の
    1.16
    ශ්
    1.12
     mici
    1.10
    ться
    1.08
     powied
    1.07
     Τ
    1.06
    થી
    1.05
    Activations Density 0.002%

    No Known Activations