© 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. 84473
    Prev
    Next
    INDEX
    Explanations

    BLACK =

    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
    is
    1.81
     was
    1.77
    t
    1.77
    o
    1.73
    a
    1.72
    was
    1.69
    es
    1.67
    it
    1.66
    et
    1.64
     and
    1.61
    POSITIVE LOGITS
    };
    1.34
    กัน
    1.34
    ますが
    1.30
    ד
    1.28
    lerde
    1.27
    (
    1.26
     постро
    1.21
    ند
    1.20
    しまう
    1.20
    കൊണ്ട്
    1.20
    Activations Density 0.000%

    No Known Activations