© 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. 151196
    Prev
    Next
    INDEX
    Explanations

    intriguing curious

    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
     اللَّ
    0.34
     який
    0.32
    ಕ್
    0.31
     כמ
    0.31
    菫
    0.31
     場所
    0.30
    }:$
    0.30
     presque
    0.30
    ⵉ
    0.30
     незале
    0.29
    POSITIVE LOGITS
     Banca
    0.34
     acet
    0.32
     warrants
    0.32
     banca
    0.31
     ladders
    0.31
    ടതി
    0.31
    organ
    0.30
     day
    0.30
    myfile
    0.30
     Funded
    0.30
    Activations Density 0.031%

    No Known Activations