© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62413
    Prev
    Next
    INDEX
    Explanations

    todos in code

    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_2_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
    0
    1.80
    -
    1.64
    ли
    1.44
    i
    1.19
    (
    1.13
    ה
    1.12
    ي
    1.11
    ０
    1.08
    י
    1.06
    ಿ
    1.03
    POSITIVE LOGITS
    ier
    1.16
     ότι
    1.13
    า
    1.10
     It
    1.01
    It
    0.98
     möj
    0.98
    ıları
    0.98
    ně
    0.96
    ো
    0.95
     thời
    0.94
    Activations Density 0.001%

    No Known Activations