© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207457
    Prev
    Next
    INDEX
    Explanations

    dendrites

    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_20_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
    What
    0.52
     mutant
    0.45
    _
    0.44
     what
    0.42
     Blood
    0.42
    Head
    0.41
     Mutant
    0.41
    -
    0.41
    Blood
    0.40
    SuppressWarnings
    0.40
    POSITIVE LOGITS
    ızı
    0.53
    隐含规则
    0.52
     दुर्घटना
    0.50
     EPR
    0.47
     méxico
    0.47
     पढ़ने
    0.46
    షన్
    0.46
     Executives
    0.45
     Règ
    0.45
    örer
    0.45
    Activations Density 0.000%

    No Known Activations