© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18196
    Prev
    Next
    INDEX
    Explanations

    directly affects

    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_34_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
     derivadas
    0.38
    俻
    0.37
    eci
    0.36
    క్కువ
    0.35
    ృష్టి
    0.34
     exag
    0.34
     chromatographed
    0.34
     strained
    0.34
    險
    0.34
     melaksanakan
    0.34
    POSITIVE LOGITS
     affecting
    0.66
     affects
    0.61
     directly
    0.60
     Directly
    0.58
    Affect
    0.55
     affect
    0.54
     Affect
    0.54
    直接
    0.54
     관련된
    0.54
     يتعلق
    0.54
    Activations Density 0.074%

    No Known Activations