© 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. 31880
    Prev
    Next
    INDEX
    Explanations

    not appropriate for

    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
     税
    0.45
    税
    0.43
     tax
    0.39
    posal
    0.39
    ົ
    0.39
     thuế
    0.38
    یین
    0.38
     Hai
    0.38
     Hoek
    0.37
     Named
    0.37
    POSITIVE LOGITS
     front
    0.37
    front
    0.36
    \|,
    0.35
    pieza
    0.35
     brokerage
    0.34
     Patients
    0.34
     朱
    0.34
    Patients
    0.33
    ZG
    0.33
    ंजनों
    0.33
    Activations Density 0.041%

    No Known Activations