© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45227
    Prev
    Next
    INDEX
    Explanations

    execute permissions

    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_22_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
    Bug
    0.52
    G
    0.52
    Colomb
    0.51
    Sch
    0.50
    Datos
    0.50
    Aby
    0.49
    р
    0.49
    Fecha
    0.47
    Nota
    0.47
    Columbia
    0.47
    POSITIVE LOGITS
     declarations
    0.59
     assurances
    0.55
     lathes
    0.48
     assuring
    0.48
     ڕ
    0.47
     arrangements
    0.47
     torches
    0.46
     trấn
    0.45
     gamanam
    0.45
     wires
    0.44
    Activations Density 0.000%

    No Known Activations