© 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
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16809
    Prev
    Next
    INDEX
    Explanations

    useful and convenient

    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_15_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
    E
    0.73
    O
    0.73
    S
    0.64
    J
    0.59
    I
    0.59
    P
    0.59
    iverse
    0.55
    U
    0.54
    V
    0.54
     O
    0.53
    POSITIVE LOGITS
     軍
    0.63
     удобно
    0.58
     наве
    0.58
     dificultades
    0.56
     conveniences
    0.56
     সুবিধ
    0.55
     relics
    0.53
     ብዙውን
    0.53
     судо
    0.52
     እንኳ
    0.52
    Activations Density 0.035%

    No Known Activations