© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195330
    Prev
    Next
    INDEX
    Explanations

    articulation, weighting, airspeed

    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_15_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
    flies
    0.50
     हमेशा
    0.49
    ’
    0.49
    cence
    0.47
    fat
    0.47
    ir
    0.46
    ides
    0.46
    yn
    0.46
     compost
    0.46
     composting
    0.46
    POSITIVE LOGITS
    ﭜ
    0.52
    Articulation
    0.51
    辔
    0.51
    ELLE
    0.50
    로
    0.50
     pob
    0.50
    сора
    0.50
    LS
    0.49
    urbo
    0.49
    льному
    0.49
    Activations Density 0.000%

    No Known Activations