© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150390
    Prev
    Next
    INDEX
    Explanations

    wider audience

    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
     Treated
    0.12
     Toma
    0.12
     verlo
    0.12
     tramite
    0.11
    }=(-
    0.11
     groupId
    0.11
     Forms
    0.11
     条
    0.11
    vano
    0.11
     Affiliate
    0.11
    POSITIVE LOGITS
    민
    0.13
    ideal
    0.12
    Ideal
    0.12
    Number
    0.11
     megold
    0.11
    如何
    0.11
    দ্‌
    0.11
    Brussels
    0.11
    How
    0.11
    Marshall
    0.11
    Activations Density 0.027%

    No Known Activations