© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59279
    Prev
    Next
    INDEX
    Explanations

    contempt

    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_2_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
    '
    1.39
     are
    1.24
    ра
    1.22
    1.13
    ри
    1.08
    س
    1.08
     adjudged
    1.00
     були
    0.97
    ),
    0.91
    </
    0.91
    POSITIVE LOGITS
    n
    1.53
    is
    1.28
    et
    1.06
    ار
    1.05
    ind
    1.02
    9
    1.00
    nade
    1.00
    ung
    0.99
    has
    0.99
    naj
    0.98
    Activations Density 0.000%

    No Known Activations