© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104028
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     Bet
    0.41
    त्म
    0.41
     grammaticality
    0.38
    侩
    0.38
    GRAM
    0.38
     Abraham
    0.38
     crum
    0.37
     hok
    0.37
     svi
    0.37
     ভালোভাবে
    0.36
    POSITIVE LOGITS
    Code
    0.42
     kode
    0.37
    unii
    0.37
    getRepository
    0.37
    code
    0.36
    uler
    0.36
    pers
    0.36
    Pw
    0.36
    ({{
    0.36
    Kode
    0.35
    Activations Density 0.089%

    No Known Activations