© 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. 217948
    Prev
    Next
    INDEX
    Explanations

    compose, made, build

    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
     pouvez
    0.41
     Sorrent
    0.37
    以上
    0.35
     puoi
    0.32
     distorted
    0.32
     surviving
    0.32
    恋
    0.31
    という
    0.31
    ုတ်
    0.30
    邺
    0.30
    POSITIVE LOGITS
    ung
    0.33
    upart
    0.32
     ReactDOM
    0.32
    up
    0.32
    eb
    0.32
    ulas
    0.32
    Mad
    0.32
    ee
    0.32
    setAction
    0.32
     allele
    0.31
    Activations Density 0.125%

    No Known Activations