© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210774
    Prev
    Next
    INDEX
    Explanations

    BSN, HSK, SQL, bsky

    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_5_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
    in
    1.16
    িন
    1.12
    𝗶
    1.05
     činjen
    1.05
    ない
    1.02
    descricao
    1.02
     edizione
    0.97
    دی
    0.96
     οποία
    0.95
     ufficial
    0.95
    POSITIVE LOGITS
    y
    1.34
    1
    1.33
    ع
    1.30
    1.16
    <0x0D>
    1.09
    ق
    0.97
     and
    0.94
    ו
    0.92
    INGS
    0.91
    ح
    0.90
    Activations Density 0.000%

    No Known Activations