© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38828
    Prev
    Next
    INDEX
    Explanations

    kill switch, kill chain, killzones

    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_3_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
    t
    0.74
    γ
    0.65
     ampli
    0.56
    tomato
    0.54
    hig
    0.54
    ತ್ಮ
    0.54
     you
    0.52
     omnichannel
    0.52
    iflower
    0.51
    κες
    0.51
    POSITIVE LOGITS
    OT
    0.78
    ET
    0.71
    ла
    0.70
    د
    0.70
    AD
    0.67
    OS
    0.67
    دين
    0.66
    OM
    0.65
     killing
    0.64
    ER
    0.64
    Activations Density 0.001%

    No Known Activations