© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52450
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by numbers or specific words

    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
    gevens
    0.44
    㿟
    0.42
    舧
    0.42
    稒
    0.41
     kuf
    0.39
    idação
    0.39
    隂
    0.39
    㡷
    0.38
    啠
    0.37
    算是
    0.37
    POSITIVE LOGITS
    Truck
    0.41
    hole
    0.35
     Truck
    0.35
     intentional
    0.35
    ↵↵↵
    0.35
    ###
    0.35
     постав
    0.34
    xx
    0.34
    truck
    0.34
    赦
    0.34
    Activations Density 0.000%

    No Known Activations