© 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. 41531
    Prev
    Next
    INDEX
    Explanations

    casino

    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
    '
    0.77
    EN
    0.68
    य
    0.66
    }
    0.65
    IL
    0.64
    ation
    0.63
    IC
    0.63
     için
    0.63
     offices
    0.63
     potrivit
    0.63
    POSITIVE LOGITS
    toContain
    0.67
    rarr
    0.67
    doctype
    0.64
    قاف
    0.64
    collectionView
    0.64
    dde
    0.64
    rées
    0.63
    resolve
    0.62
    鳎
    0.61
    dQ
    0.61
    Activations Density 0.000%

    No Known Activations