© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5212
    Prev
    Next
    INDEX
    Explanations

    social media platforms and communication styles

    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_39_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
    plash
    0.31
     برگ
    0.31
     Patrol
    0.30
     patrol
    0.30
    PerRow
    0.30
    慌
    0.29
    рами
    0.29
     vermel
    0.29
    женной
    0.29
    泼
    0.29
    POSITIVE LOGITS
    amy
    0.33
     riffs
    0.31
     linkedin
    0.29
     minds
    0.29
     jan
    0.29
    choose
    0.29
     mús
    0.28
    pheus
    0.28
     Ghan
    0.28
    uyễn
    0.28
    Activations Density 0.032%

    No Known Activations