© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208799
    Prev
    Next
    INDEX
    Explanations

    knowledge management

    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_10_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
    et
    0.91
    ä
    0.80
    ah
    0.80
    is
    0.78
    as
    0.78
    f
    0.77
    eg
    0.75
    se
    0.73
    t
    0.73
    é
    0.72
    POSITIVE LOGITS
    ]
    0.89
    )
    0.71
    คุ
    0.68
    崆
    0.67
     axiom
    0.66
     Алла
    0.66
    فی
    0.66
    โน
    0.66
     insulators
    0.66
     समीप
    0.66
    Activations Density 0.011%

    No Known Activations