© 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. 78340
    Prev
    Next
    INDEX
    Explanations

    Access-Control-Allow-Origin header

    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
     ped
    0.41
    明
    0.38
    TY
    0.37
     RMS
    0.37
    agus
    0.37
     cla
    0.36
    Intent
    0.36
     paucity
    0.36
    文字
    0.36
     Inspir
    0.36
    POSITIVE LOGITS
     vertebra
    0.38
    無論
    0.38
     فوټبال
    0.37
    inars
    0.36
    ہرست
    0.36
    ним
    0.35
    VELOP
    0.35
    ;')
    0.35
    hurricane
    0.35
    ௦
    0.35
    Activations Density 0.002%

    No Known Activations