© 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. 103974
    Prev
    Next
    INDEX
    Explanations

    names and brands

    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
     Oct
    0.38
    ח
    0.36
     stres
    0.35
    sealed
    0.35
    Oct
    0.35
     OCTOBER
    0.34
    穸
    0.34
    ௦
    0.34
     octobre
    0.34
     parfaitement
    0.34
    POSITIVE LOGITS
     plc
    0.49
    Renewal
    0.42
     intrans
    0.41
    停
    0.38
     তারপরে
    0.37
     Tanık
    0.36
     및
    0.35
     erinn
    0.35
     PLC
    0.35
    <unused32>
    0.35
    Activations Density 0.012%

    No Known Activations