© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12117
    Prev
    Next
    INDEX
    Explanations

    introducing accompanying details

    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_13_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
    ž
    0.71
    ’),
    0.57
    getCql
    0.57
     অবলম্বন
    0.56
     Madhya
    0.55
     Martial
    0.55
     razão
    0.54
     வலு
    0.54
     நினைக்க
    0.54
     வைக்க
    0.54
    POSITIVE LOGITS
    zug
    0.53
    mint
    0.48
    ing
    0.45
    <0x80>
    0.45
    zont
    0.45
    p
    0.45
     hoi
    0.44
    具
    0.43
    yay
    0.43
    y
    0.43
    Activations Density 0.081%

    No Known Activations