© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233970
    Prev
    Next
    INDEX
    Explanations

    summer and August

    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_32_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
     cross
    0.35
    cross
    0.32
     Increased
    0.28
     shape
    0.27
    模
    0.27
    卸
    0.26
     strain
    0.26
     titan
    0.26
    CROSS
    0.26
     comfortably
    0.26
    POSITIVE LOGITS
     summertime
    0.35
     летом
    0.34
    Insect
    0.34
    Summer
    0.33
    夏
    0.32
    夏季
    0.32
     夏
    0.31
     夏季
    0.30
    Ent
    0.30
     insect
    0.30
    Activations Density 0.000%

    No Known Activations