© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6394
    Prev
    Next
    INDEX
    Explanations

    incident handling EFF

    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_39_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
    मोल
    0.30
    數據
    0.29
    perturbative
    0.28
    ⼈
    0.28
     Gesù
    0.27
    怨
    0.27
    ၵ
    0.27
    Ἐ
    0.27
    க்கெ
    0.26
    データ
    0.26
    POSITIVE LOGITS
    oney
    0.32
    Prime
    0.28
    fac
    0.26
     mr
    0.26
     Ernst
    0.26
    urrences
    0.26
     HCM
    0.26
    checks
    0.25
     capital
    0.25
     ACM
    0.25
    Activations Density 0.000%

    No Known Activations