© 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. 18806
    Prev
    Next
    INDEX
    Explanations

    consequences, infringement, piracy

    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
     maliciously
    0.57
     fdPar
    0.54
    ಾಂಶ
    0.52
    aeskeygenassist
    0.51
    xRt
    0.50
    reflectionMap
    0.49
     )$
    0.49
     منسل
    0.49
    getImageFolder
    0.46
     ಬಾ
    0.46
    POSITIVE LOGITS
     résultat
    0.51
    self
    0.51
     spindle
    0.50
     BMC
    0.50
     thicker
    0.49
    viewModel
    0.49
    𝑔
    0.49
     luctus
    0.49
     quedan
    0.48
    计划
    0.48
    Activations Density 0.005%

    No Known Activations