© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53328
    Prev
    Next
    INDEX
    Explanations

    phase 1 or step 1

    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_30_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
     or
    0.44
    或
    0.43
    หรือ
    0.43
     یا
    0.41
    ಸ್
    0.40
     அல்லது
    0.40
    ક
    0.39
     বা
    0.39
     किंवा
    0.38
     $("
    0.37
    POSITIVE LOGITS
    Medium
    0.38
    ොර
    0.36
     moyens
    0.35
     náv
    0.35
     несмотря
    0.35
     pelayanan
    0.34
    格局
    0.34
     thermodynam
    0.33
     če
    0.33
    Pole
    0.33
    Activations Density 0.001%

    No Known Activations