© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6796
    Prev
    Next
    INDEX
    Explanations

    dependency management structure

    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_39_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
    oksi
    0.27
    瞞
    0.26
    瞒
    0.26
     fejleszt
    0.26
    殤
    0.26
     Guam
    0.25
     обязан
    0.25
     소재
    0.25
    achy
    0.25
    aluminum
    0.25
    POSITIVE LOGITS
     chase
    0.28
     lawns
    0.27
    риста
    0.26
    (',',$
    0.26
     carve
    0.26
    sel
    0.26
    taskList
    0.25
     grind
    0.25
     exclusionary
    0.25
    NEGATIVE
    0.24
    Activations Density 0.003%

    No Known Activations