© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    progress

    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
    predicate
    0.46
     międzynarod
    0.46
    ဇ
    0.42
     международ
    0.41
     Международ
    0.40
     bracket
    0.39
     wyróż
    0.38
    Funding
    0.38
    Predicate
    0.38
    匁
    0.38
    POSITIVE LOGITS
    icul
    0.44
    空
    0.40
     progress
    0.38
     mac
    0.37
    progress
    0.37
     reflecting
    0.36
    iculas
    0.36
     Progress
    0.36
     PROGRESS
    0.35
    帐
    0.35
    Activations Density 0.061%

    No Known Activations