© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231069
    Prev
    Next
    INDEX
    Explanations

    occurrence of death

    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_6_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
    ität
    1.09
    ća
    0.94
    lja
    0.93
     bicovariant
    0.93
    ęcia
    0.91
    ING
    0.89
    abod
    0.88
    ъ
    0.86
    ază
    0.84
    hounds
    0.84
    POSITIVE LOGITS
    in
    1.20
     was
    1.05
    p
    1.05
    to
    1.04
     to
    0.98
    id
    0.95
    ני
    0.93
     were
    0.92
    -
    0.92
    self
    0.90
    Activations Density 0.000%

    No Known Activations