© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241220
    Prev
    Next
    INDEX
    Explanations

    988 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_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
    垀
    0.30
     relacion
    0.26
    樣子
    0.26
    域名
    0.26
     життя
    0.26
     Sundays
    0.25
    ആ
    0.24
    必要がある
    0.23
    題
    0.23
     їх
    0.23
    POSITIVE LOGITS
    AFS
    0.25
    '<
    0.24
     artisan
    0.24
     Markus
    0.24
     ISIS
    0.24
    unning
    0.24
     पाहून
    0.24
     checkout
    0.23
    简
    0.23
     scholar
    0.23
    Activations Density 0.001%

    No Known Activations