© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165398
    Prev
    Next
    INDEX
    Explanations

    member in high regard

    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
     de
    0.73
    由
    0.55
    a
    0.54
    ไม่
    0.53
     die
    0.52
     gotta
    0.52
     do
    0.52
    년을
    0.52
     di
    0.50
     had
    0.50
    POSITIVE LOGITS
    ности
    0.63
    ennzeichnet
    0.58
    alag
    0.55
    瘀
    0.55
    supportsFocus
    0.55
    MSFont
    0.54
    /";
    0.54
    InfoPlistPath
    0.54
    备案
    0.53
    {|\
    0.53
    Activations Density 0.000%

    No Known Activations