© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50919
    Prev
    Next
    INDEX
    Explanations

    biosphere, human, processes, environment

    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_31_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
     Arist
    0.41
    栥
    0.38
     arist
    0.37
     জিৎ
    0.36
     Genealogy
    0.36
    Arist
    0.36
     عايز
    0.35
    পশ্চিম
    0.35
    𒌨
    0.35
    diagonal
    0.35
    POSITIVE LOGITS
    ັນ
    0.41
     Seda
    0.39
     Planetary
    0.36
    POC
    0.36
     POC
    0.36
     PO
    0.36
     greenhouse
    0.36
     sứ
    0.35
     Greenhouse
    0.35
    ukary
    0.35
    Activations Density 0.031%

    No Known Activations