© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165288
    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_13_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
    ต้องการ
    0.47
    <0xD3>
    0.46
    by
    0.45
    0
    0.45
    hint
    0.45
    fif
    0.44
    xz
    0.41
    imary
    0.41
    <
    0.41
    xy
    0.40
    POSITIVE LOGITS
     cruel
    0.50
    issons
    0.49
     préparer
    0.49
     preparação
    0.49
     embossed
    0.49
     famously
    0.48
     تیاری
    0.47
     година
    0.47
     preparar
    0.46
     Rams
    0.46
    Activations Density 0.000%

    No Known Activations