© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201165
    Prev
    Next
    INDEX
    Explanations

    logical AND

    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
     ಹೊಂದಿದೆ
    0.38
     cherries
    0.37
    phrine
    0.37
     ইং
    0.37
    ิ่น
    0.36
    楂
    0.36
    पयोग
    0.36
     مشغول
    0.36
    veno
    0.35
    .~(\
    0.35
    POSITIVE LOGITS
     nons
    0.42
    itled
    0.39
    not
    0.38
     sandy
    0.37
     Information
    0.37
    dirty
    0.37
    expect
    0.35
    frames
    0.35
    hart
    0.35
     NOT
    0.34
    Activations Density 0.004%

    No Known Activations