© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149280
    Prev
    Next
    INDEX
    Explanations

    agree to terms

    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_23_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
    र्टी
    0.39
     calent
    0.39
    政府采购
    0.39
    ፌ
    0.38
    人民政府
    0.38
    валось
    0.38
    浓度
    0.37
     inputText
    0.37
    োর্ট
    0.37
     tatou
    0.36
    POSITIVE LOGITS
    ʬ
    0.42
     excuses
    0.40
     denials
    0.38
     aggregate
    0.38
     unauthorized
    0.38
    Чер
    0.37
    できない
    0.36
     aggregated
    0.36
    workout
    0.36
    로나
    0.36
    Activations Density 0.000%

    No Known Activations