© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211027
    Prev
    Next
    INDEX
    Explanations

    seek and file manipulation

    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_19_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
     Rebels
    0.46
     x
    0.44
     =
    0.42
     Text
    0.42
     Skip
    0.41
     p
    0.41
     circuit
    0.41
     Snow
    0.41
     c
    0.41
     mere
    0.41
    POSITIVE LOGITS
    吋
    0.48
     শব
    0.46
     operativa
    0.46
    ā
    0.46
    ارہ
    0.46
     funer
    0.45
    ଢ
    0.45
    inguistic
    0.44
    IBAction
    0.44
     kā
    0.44
    Activations Density 0.002%

    No Known Activations