© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211353
    Prev
    Next
    INDEX
    Explanations

    red teaming

    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_5_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
    j
    1.45
    1.45
    c
    1.35
    ق
    1.23
    the
    1.17
     i
    1.14
    ج
    1.10
    _
    1.09
    ع
    1.05
    .
    1.00
    POSITIVE LOGITS
     to
    1.14
    с
    1.14
     in
    1.13
    ς
    1.13
    ”
    1.07
     at
    1.06
    ’
    0.95
    го
    0.93
    ological
    0.90
    ด
    0.89
    Activations Density 0.000%

    No Known Activations