© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205606
    Prev
    Next
    INDEX
    Explanations

    code/inputs/task details

    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_25_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
    ライト
    0.34
     cahaya
    0.34
    神
    0.34
    Nunca
    0.33
    Consec
    0.33
    LGBT
    0.33
    élect
    0.33
    CRS
    0.33
    上市
    0.33
    神的
    0.32
    POSITIVE LOGITS
     Piccolo
    0.36
    ◞
    0.34
    нули
    0.32
     Ibu
    0.31
     Tasks
    0.31
     BETTER
    0.31
     MessageBox
    0.30
     образовањем
    0.30
     Instruction
    0.30
     SOME
    0.29
    Activations Density 0.008%

    No Known Activations