© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175690
    Prev
    Next
    INDEX
    Explanations

    dotted decimal notation

    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
    gevity
    0.43
    غ
    0.43
    idine
    0.42
    וף
    0.42
    Результа
    0.42
    žený
    0.42
    >{</
    0.41
    apt
    0.40
    pex
    0.40
    ++)
    0.40
    POSITIVE LOGITS
     Flock
    0.51
    સિ
    0.50
     sinais
    0.47
     composants
    0.47
     COMPONENTS
    0.46
     mosa
    0.46
     रेग
    0.46
     Embro
    0.46
     HSPB
    0.45
     ஆசிரிய
    0.45
    Activations Density 0.003%

    No Known Activations