© 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. 30743
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     minerals
    0.32
     aproximadamente
    0.30
     Minerals
    0.27
     thunder
    0.26
     allotted
    0.26
    有多少
    0.26
    annuation
    0.26
    %.
    0.25
     parasites
    0.25
     scrutiny
    0.25
    POSITIVE LOGITS
     stag
    0.26
    Apa
    0.26
    Illustration
    0.25
     Capabilities
    0.25
    ྔ
    0.25
    Transactions
    0.25
    слов
    0.25
     işlemler
    0.24
    Maya
    0.24
     permit
    0.24
    Activations Density 0.007%

    No Known Activations