© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199386
    Prev
    Next
    INDEX
    Explanations

    `as` or `shijing`

    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_15_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
    ài
    0.46
    }=\
    0.45
    EVENT
    0.44
    Presence
    0.44
    Alessandro
    0.44
    IR
    0.44
    Flowers
    0.44
    Executing
    0.43
    Steel
    0.43
    Vine
    0.42
    POSITIVE LOGITS
     dispersion
    0.58
     renom
    0.53
     authorized
    0.50
     begun
    0.50
    囗
    0.50
     hund
    0.50
    丶
    0.50
     孔
    0.49
    მოს
    0.49
     നേതൃ
    0.49
    Activations Density 0.000%

    No Known Activations