© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108306
    Prev
    Next
    INDEX
    Explanations

    kill signal termination

    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_1_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
    ’
    1.61
    ↵↵
    1.34
    ó
    1.24
     rápid
    1.22
     médicas
    1.22
    ק
    1.19
     significativas
    1.16
    ෙන්
    1.13
     régler
    1.12
    м
    1.12
    POSITIVE LOGITS
    us
    1.32
    ning
    1.20
    den
    1.10
    ties
    1.09
    il
    1.05
    ts
    1.05
    ting
    1.04
    uc
    1.03
    nd
    1.02
    ses
    1.02
    Activations Density 0.001%

    No Known Activations