© 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. 87551
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     αρχ
    0.66
    流畅
    0.62
    ه
    0.61
    a
    0.59
     అర్థ
    0.59
    ellt
    0.58
     sawdust
    0.55
    لس
    0.55
    لي
    0.54
    aaf
    0.54
    POSITIVE LOGITS
    <0x0D>
    0.84
     are
    0.79
     be
    0.74
    ü
    0.69
    та
    0.67
     can
    0.66
    માં
    0.64
    मन
    0.63
    मे
    0.63
    ,|\
    0.62
    Activations Density 0.000%

    No Known Activations