© 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. 261470
    Prev
    Next
    INDEX
    Explanations

    curly braces or brackets

    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
     කාල
    0.42
    ज्ञ
    0.40
    efficacy
    0.40
    ྕ
    0.40
    encoders
    0.38
    sendFile
    0.37
    前後
    0.36
    pleasant
    0.36
     Regression
    0.36
    忝
    0.36
    POSITIVE LOGITS
    під
    0.46
     président
    0.44
    مارات
    0.41
     Unis
    0.40
    geordnet
    0.40
     started
    0.40
     sprouted
    0.40
    ပေါ
    0.39
     Unterricht
    0.39
    總統
    0.39
    Activations Density 0.003%

    No Known Activations