© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198291
    Prev
    Next
    INDEX
    Explanations

    Klaus Richter or artichoke dip

    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_4_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
    el
    1.00
    p
    0.92
    k
    0.88
    h
    0.86
     de
    0.83
    ل
    0.83
    ar
    0.82
     die
    0.81
     gift
    0.80
    b
    0.80
    POSITIVE LOGITS
    ?
    0.88
    স
    0.85
    )।
    0.85
    ।
    0.82
    種の
    0.81
    landı
    0.79
     abiertos
    0.77
    PO
    0.77
     It
    0.76
    はじ
    0.74
    Activations Density 0.000%

    No Known Activations