© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43199
    Prev
    Next
    INDEX
    Explanations

    voice assistants, reputation, transcript

    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_3_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
     gehört
    0.57
     impediments
    0.56
    S
    0.55
    lık
    0.54
     семейства
    0.53
    "));
    0.52
     ausgeführt
    0.52
    Ě
    0.52
    )");
    0.52
     terdiri
    0.52
    POSITIVE LOGITS
    螓
    0.76
    ink
    0.75
    as
    0.74
    dien
    0.67
    because
    0.66
    times
    0.64
    rind
    0.64
    bowtie
    0.62
    ਭ
    0.62
    认真
    0.61
    Activations Density 0.014%

    No Known Activations