© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195703
    Prev
    Next
    INDEX
    Explanations

    multiple of

    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_15_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
     н
    0.29
     infe
    0.27
     lobes
    0.27
     gills
    0.27
     cracking
    0.27
     ấm
    0.27
     idiots
    0.26
    not
    0.26
     глав
    0.26
     اړ
    0.26
    POSITIVE LOGITS
    䛺
    0.26
    ਈ
    0.25
     negara
    0.24
    UIColor
    0.24
    ,"%
    0.24
    🏷
    0.24
    家族
    0.24
     Negara
    0.23
    くり
    0.23
    治療
    0.23
    Activations Density 0.005%

    No Known Activations