© 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. 17848
    Prev
    Next
    INDEX
    Explanations

    Source

    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
    น
    0.31
    pcl
    0.30
    ن
    0.29
    plotting
    0.29
    P
    0.28
     plexus
    0.28
    Willow
    0.28
    ActionButton
    0.28
    Glam
    0.27
     pradesh
    0.27
    POSITIVE LOGITS
     କରି
    0.36
     describing
    0.34
     ("
    0.32
     descre
    0.32
     partnered
    0.31
     referenced
    0.30
    ução
    0.30
     "
    0.30
    úncia
    0.30
     Pron
    0.29
    Activations Density 0.027%

    No Known Activations