© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83663
    Prev
    Next
    INDEX
    Explanations

    suicidal ideation or signs

    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_29_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
    ugía
    0.37
    iembre
    0.36
     vog
    0.36
    oxy
    0.36
     Kalian
    0.36
    攒
    0.35
    est
    0.35
    apine
    0.34
    组成的
    0.34
     Vag
    0.33
    POSITIVE LOGITS
     vulnerable
    0.48
     sensitive
    0.47
     znak
    0.43
     detection
    0.42
     signs
    0.42
     गुणा
    0.39
    隣
    0.39
     perceptive
    0.39
    detection
    0.38
     detections
    0.38
    Activations Density 0.023%

    No Known Activations