© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44139
    Prev
    Next
    INDEX
    Explanations

    `go` to other 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_22_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
     самый
    0.28
    xiety
    0.25
     plaf
    0.25
     propaganda
    0.24
    });
    0.24
    đ
    0.24
    }]
    0.23
    addock
    0.23
     যাইহোক
    0.23
     слишком
    0.23
    POSITIVE LOGITS
    信する
    0.28
     haired
    0.27
    ാനെ
    0.26
    WebServlet
    0.25
     gahet
    0.24
    くなった
    0.24
     Dien
    0.23
     kancel
    0.23
    껄
    0.23
    Fish
    0.23
    Activations Density 0.000%

    No Known Activations