© 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. 176065
    Prev
    Next
    INDEX
    Explanations

    campaigns

    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
     sostegno
    0.35
     mètres
    0.32
     Redd
    0.32
     abrió
    0.32
    Referències
    0.31
    嫐
    0.30
     Audience
    0.30
    itumor
    0.30
     amerikan
    0.30
    getRed
    0.30
    POSITIVE LOGITS
    之一
    0.33
    var
    0.32
    ร
    0.31
    ーツ
    0.30
    變
    0.30
    蒂
    0.30
    ตาม
    0.29
    ovka
    0.29
    以
    0.29
    +
    0.29
    Activations Density 0.002%

    No Known Activations