© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143278
    Prev
    Next
    INDEX
    Explanations

    range, world, devices, accessories, items

    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_0_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
    ;
    2.02
     was
    1.42
    "
    1.28
    </h2>
    1.22
    cego
    1.21
    <0x0D>
    1.17
    ],
    1.17
     venezol
    1.17
    .},
    1.16
    েও
    1.16
    POSITIVE LOGITS
    ل
    1.69
    l
    1.67
    д
    1.62
    ס
    1.60
    د
    1.58
     in
    1.57
    ש
    1.53
    מ
    1.48
    ל
    1.44
    s
    1.42
    Activations Density 0.000%

    No Known Activations