© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57282
    Prev
    Next
    INDEX
    Explanations

    network interface names

    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_11_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
    ੋ
    0.57
    。「
    0.49
     delicate
    0.49
    。【
    0.48
    Α
    0.48
    логов
    0.48
    ן
    0.45
     divine
    0.45
    ื้อ
    0.45
    腹
    0.45
    POSITIVE LOGITS
    बारा
    0.60
    Phrase
    0.52
     కారణంగా
    0.51
     Otras
    0.50
     conversaciones
    0.50
     społec
    0.50
    鏟
    0.50
     propias
    0.50
    ichi
    0.49
    ebb
    0.48
    Activations Density 0.000%

    No Known Activations