© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221581
    Prev
    Next
    INDEX
    Explanations

    City Bus, child checks

    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_10_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
     आपको
    0.50
     ies
    0.49
    ؟
    0.48
    ㅣ
    0.48
     इन्हे
    0.46
     kostet
    0.46
    休憩
    0.46
     $=\
    0.46
    த்தையும்
    0.45
    います
    0.45
    POSITIVE LOGITS
    aol
    0.44
     racial
    0.43
     stab
    0.43
    g
    0.43
    Infer
    0.43
    ac
    0.42
    ла
    0.42
    कुमार
    0.41
    Elephant
    0.41
    سكرية
    0.41
    Activations Density 0.000%

    No Known Activations