© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134940
    Prev
    Next
    INDEX
    Explanations

    opacities

    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_6_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
    å
    0.90
     fluorescent
    0.89
     spectre
    0.89
     shimmering
    0.88
     batt
    0.86
    )
    0.86
     viscous
    0.84
     thermoplastic
    0.84
     fashioned
    0.84
     seism
    0.83
    POSITIVE LOGITS
    al
    1.16
    ни
    1.12
    ll
    1.11
    ką
    1.09
    so
    1.07
    و
    1.07
    love
    1.05
    7
    1.05
    з
    1.05
    9
    1.05
    Activations Density 0.000%

    No Known Activations