© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10543
    Prev
    Next
    INDEX
    Explanations

    prompt syntax

    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_13_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
    ز
    0.49
    ٢
    0.45
    colour
    0.44
    systems
    0.44
    ብር
    0.43
    vere
    0.43
    ";
    0.42
    ెర
    0.42
    バード
    0.42
     बताएंगे
    0.41
    POSITIVE LOGITS
     mundo
    0.50
     quanto
    0.49
     tonnage
    0.47
     accum
    0.47
     gigante
    0.45
     profonde
    0.45
    Shr
    0.45
     Prothorax
    0.45
    ENIDO
    0.45
     crumb
    0.44
    Activations Density 0.028%

    No Known Activations