© 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. 126172
    Prev
    Next
    INDEX
    Explanations

    preferred

    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
    िफ्ट
    0.84
    ك
    0.71
     préf
    0.68
    Bus
    0.68
    Preferred
    0.67
    R
    0.67
    س
    0.65
    Bon
    0.64
    preference
    0.64
    of
    0.64
    POSITIVE LOGITS
    '
    0.71
    )
    0.66
    ă
    0.66
    ;
    0.65
    .’
    0.62
    .
    0.62
     a
    0.60
     n
    0.60
     by
    0.60
     d
    0.60
    Activations Density 0.003%

    No Known Activations