© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79979
    Prev
    Next
    INDEX
    Explanations

    UI development components

    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_31_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
     Composition
    0.43
     latar
    0.43
    ющиеся
    0.42
     unfamiliar
    0.42
     cryptographic
    0.41
     कैन
    0.40
    渊
    0.40
    击
    0.39
     именно
    0.38
    භ
    0.38
    POSITIVE LOGITS
    conder
    0.41
    metro
    0.40
    ensky
    0.40
    arta
    0.39
    indler
    0.39
    出自
    0.39
    sale
    0.38
    district
    0.38
    heta
    0.38
    grove
    0.38
    Activations Density 0.004%

    No Known Activations