© 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. 85916
    Prev
    Next
    INDEX
    Explanations

    Robert followed by name

    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
     NACA
    0.62
     되
    0.60
    성은
    0.59
     warum
    0.55
     GTS
    0.54
    Wei
    0.54
    篑
    0.53
    <h2>
    0.53
     ا
    0.52
    氐
    0.52
    POSITIVE LOGITS
    the
    0.89
    r
    0.85
    는
    0.84
    ۔
    0.82
    は
    0.80
    ید
    0.79
    కు
    0.75
    ла
    0.72
    க்கு
    0.68
    কে
    0.68
    Activations Density 0.001%

    No Known Activations