© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 109076
    Prev
    Next
    INDEX
    Explanations

    Pilbara Minerals region

    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_1_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
    x
    1.27
    ast
    1.18
    il
    1.14
    ara
    1.13
    and
    1.09
    as
    1.05
    ay
    1.05
    us
    1.04
    ug
    0.99
     А
    0.97
    POSITIVE LOGITS
    I
    1.48
    ли
    1.39
    י
    1.29
    ۔
    1.23
    }
    1.17
    ي
    1.16
    是
    1.16
    は
    1.07
     publié
    1.06
    U
    1.06
    Activations Density 0.001%

    No Known Activations