© 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. 261320
    Prev
    Next
    INDEX
    Explanations

    install.packages

    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
    鈦
    0.20
    獾
    0.18
     motivo
    0.17
    ņa
    0.17
     फिन
    0.16
    ason
    0.16
    phal
    0.16
    ہار
    0.16
    otiv
    0.16
    듐
    0.16
    POSITIVE LOGITS
     Z
    0.16
    Zv
    0.16
    方
    0.16
     Thunder
    0.16
     EPR
    0.16
     UE
    0.16
    奉
    0.15
     CREATE
    0.15
    堅
    0.15
     Zhe
    0.15
    Activations Density 0.001%

    No Known Activations