© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132910
    Prev
    Next
    INDEX
    Explanations

    betrothed to

    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
    .
    1.57
    utte
    1.06
    ild
    1.05
    ron
    1.05
    ilan
    1.02
    rom
    0.99
    uen
    0.96
    alli
    0.95
    iv
    0.95
     Даже
    0.94
    POSITIVE LOGITS
    ون
    1.66
    s
    1.39
    >
    1.38
    }
    1.37
    ల
    1.34
    e
    1.25
    ي
    1.20
    ని
    1.19
    o
    1.19
    ни
    1.18
    Activations Density 0.001%

    No Known Activations