© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35170
    Prev
    Next
    INDEX
    Explanations

    starts with or followed by

    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
     Trigon
    0.40
    com
    0.39
    ത്തിന്
    0.38
    HeaderParams
    0.38
     richly
    0.37
    cept
    0.37
     Esso
    0.36
    ᐟ
    0.36
    meth
    0.36
    ኘት
    0.36
    POSITIVE LOGITS
     Faculties
    0.38
    定位
    0.36
     invasive
    0.36
     molecular
    0.35
    随机
    0.35
     stochastic
    0.35
    鰭
    0.35
     electron
    0.34
     evento
    0.34
     literary
    0.34
    Activations Density 0.004%

    No Known Activations