© 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. 131768
    Prev
    Next
    INDEX
    Explanations

    Risk and risk tolerance

    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
    in
    0.96
    י
    0.91
    )
    0.90
    ]
    0.90
    .
    0.90
    ف
    0.85
    ו
    0.84
    i
    0.81
    ي
    0.81
    ні
    0.80
    POSITIVE LOGITS
    p
    1.08
    <0x0D>
    0.87
    (),
    0.87
    ’,
    0.77
     that
    0.73
    enu
    0.73
    ()<<"
    0.71
    시면
    0.69
    پ
    0.69
    pV
    0.68
    Activations Density 0.009%

    No Known Activations