© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172566
    Prev
    Next
    INDEX
    Explanations

    instructions to tailor or gather information

    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_20_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
    apps
    0.30
    yards
    0.28
    confirmation
    0.27
    x
    0.26
    خستان
    0.25
    outs
    0.25
    moved
    0.25
    ield
    0.25
    en
    0.24
     also
    0.24
    POSITIVE LOGITS
    著名的
    0.31
    其他的
    0.29
    的路
    0.27
     路
    0.26
    觕
    0.26
     প্রাস
    0.26
     Ө
    0.26
     Vorg
    0.25
     Paine
    0.25
     В
    0.25
    Activations Density 0.003%

    No Known Activations