© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87608
    Prev
    Next
    INDEX
    Explanations

    plant genus and species

    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_18_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
    畂
    0.37
     Precinct
    0.36
     privind
    0.34
     Appropriations
    0.34
     indipendente
    0.34
    腖
    0.34
    秵
    0.34
     compétition
    0.33
     Acupuncture
    0.33
     ස්ථා
    0.33
    POSITIVE LOGITS
    this
    0.33
    that
    0.30
    e
    0.30
    after
    0.29
     ,
    0.29
    order
    0.29
    what
    0.29
    had
    0.29
    ignore
    0.29
    iv
    0.28
    Activations Density 0.004%

    No Known Activations