© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102807
    Prev
    Next
    INDEX
    Explanations

    scoop of protein powder

    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_16_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
    Vegan
    0.61
    lectual
    0.55
    Scan
    0.55
     земле
    0.54
    船
    0.53
    стики
    0.53
    Intelligence
    0.52
    Vine
    0.52
    Typography
    0.52
    Ven
    0.51
    POSITIVE LOGITS
     guitarist
    0.64
     adjustment
    0.58
     wildcard
    0.55
     hippie
    0.55
    邝
    0.55
     esas
    0.53
    df
    0.53
     df
    0.52
     player
    0.52
     如果
    0.52
    Activations Density 0.000%

    No Known Activations