© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138008
    Prev
    Next
    INDEX
    Explanations

    Suicide & Crisis Lifeline

    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_12_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
     to
    0.32
     no
    0.31
     本
    0.30
    no
    0.30
     सत्य
    0.29
     all
    0.29
     U
    0.29
    er
    0.29
     నా
    0.29
     Ut
    0.28
    POSITIVE LOGITS
    ！)
    0.27
    稩
    0.26
     எளி
    0.26
     logro
    0.26
     peacetime
    0.26
     phim
    0.26
     Prothorax
    0.25
    বরা
    0.25
     कहे
    0.25
     shenanigans
    0.25
    Activations Density 0.001%

    No Known Activations