© 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. 103475
    Prev
    Next
    INDEX
    Explanations

    establishes

    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
    ма
    1.07
     Weitere
    0.95
    Geb
    0.92
    ،
    0.92
    بير
    0.89
    Kap
    0.87
     allgeme
    0.86
    }=
    0.86
    ategorie
    0.86
     అయితే
    0.86
    POSITIVE LOGITS
     with
    1.45
    y
    1.39
     from
    1.37
    ר
    1.34
    ס
    1.27
     on
    1.27
    n
    1.25
    g
    1.24
    ע
    1.23
    т
    1.19
    Activations Density 0.001%

    No Known Activations