© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214324
    Prev
    Next
    INDEX
    Explanations

    say '-'

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     hồn
    0.37
    __.__
    0.37
    얀
    0.36
    பாடு
    0.36
    CIES
    0.34
    ائر
    0.33
     goal
    0.33
     અંગ
    0.33
    ServletContext
    0.33
    精确
    0.33
    POSITIVE LOGITS
    ‐
    0.46
    ־
    0.41
    postgresql
    0.40
    usd
    0.40
    hyd
    0.39
    ‑
    0.39
    essive
    0.38
    كتب
    0.38
    expired
    0.37
    pacific
    0.37
    Activations Density 0.003%

    No Known Activations