© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 81010
    Prev
    Next
    INDEX
    Explanations

    }end;

    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_29_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
     Hawk
    0.33
    ˌ
    0.32
    attr
    0.31
    doctrine
    0.31
    elbow
    0.30
    atos
    0.29
    ˈ
    0.29
    ودة
    0.29
    저
    0.28
    Hawk
    0.28
    POSITIVE LOGITS
    考察
    0.32
     melodrama
    0.31
     reckon
    0.30
     banter
    0.30
     López
    0.29
     tavern
    0.29
     tequila
    0.29
     îm
    0.29
     pancakes
    0.29
     unintended
    0.29
    Activations Density 0.000%

    No Known Activations