© 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. 46383
    Prev
    Next
    INDEX
    Explanations

    you change

    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
    는
    0.97
    I
    0.90
    ఈ
    0.90
     I
    0.86
    }.
    0.85
    は
    0.84
    எ
    0.81
    ').
    0.80
    ં
    0.75
    ఆ
    0.74
    POSITIVE LOGITS
    on
    1.08
     on
    0.95
    ai
    0.87
    ow
    0.85
     deserial
    0.84
    osas
    0.79
     retorn
    0.78
    obar
    0.77
    ok
    0.77
     chopper
    0.76
    Activations Density 0.000%

    No Known Activations