© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199839
    Prev
    Next
    INDEX
    Explanations

    streamlit

    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_46_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
    maq
    0.41
    夰
    0.39
    扞
    0.38
     Wis
    0.37
     literally
    0.37
     illuminating
    0.36
    بخ
    0.36
    ጥ
    0.36
     disrupted
    0.36
    촤
    0.36
    POSITIVE LOGITS
     прийня
    0.43
     پذیر
    0.41
    Kat
    0.40
     چلے
    0.39
    𓍊
    0.38
     મને
    0.38
    적이
    0.38
    NU
    0.38
     pentes
    0.37
    нути
    0.36
    Activations Density 0.000%

    No Known Activations