© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209877
    Prev
    Next
    INDEX
    Explanations

    making a choice

    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_5_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
    t
    2.13
    tif
    1.20
    tn
    1.19
    tive
    1.13
    tan
    1.12
    tale
    1.10
    tion
    1.05
    tions
    1.05
    tR
    1.04
    től
    1.01
    POSITIVE LOGITS
    。
    1.18
    ۔
    1.01
    .
    0.95
     I
    0.95
    '
    0.94
    EAR
    0.93
     しかし
    0.87
     \
    0.86
     historian
    0.85
    ны
    0.85
    Activations Density 0.009%

    No Known Activations