© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60373
    Prev
    Next
    INDEX
    Explanations

    suicide prevention, self-mockery, grief, risk

    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_2_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
    -
    1.27
    1.16
    ama
    1.05
     of
    1.04
    การ
    0.96
    v
    0.95
    場合は
    0.93
    4
    0.93
    时候
    0.93
    کر
    0.90
    POSITIVE LOGITS
    ور
    1.23
    ل
    1.14
    ů
    1.11
    as
    1.08
    ラ
    1.07
    IN
    1.05
    ر
    1.05
    ul
    0.99
    ів
    0.99
    ým
    0.98
    Activations Density 0.001%

    No Known Activations