© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88082
    Prev
    Next
    INDEX
    Explanations

    Sushi Express

    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
    j
    0.76
    。
    0.73
     it
    0.72
     concili
    0.72
    ли
    0.66
     sépt
    0.66
     can
    0.65
     pregunt
    0.64
    Solver
    0.63
     be
    0.63
    POSITIVE LOGITS
    1
    0.95
    ள்
    0.61
    ل
    0.61
    ell
    0.61
    鲍
    0.61
    ان
    0.59
    ι
    0.59
    nehmens
    0.58
    다
    0.58
    শান্ত
    0.56
    Activations Density 0.000%

    No Known Activations