© 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. 32979
    Prev
    Next
    INDEX
    Explanations

    API operations GET POST PUT DELETE

    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
    逸
    0.38
    ท่าน
    0.38
     お客様
    0.37
    ेशनल
    0.37
    玦
    0.37
     वाक्यांश
    0.36
     தவற
    0.36
     handed
    0.36
    ʄ
    0.36
     fontstyle
    0.35
    POSITIVE LOGITS
     full
    0.38
     inward
    0.38
    Update
    0.36
     complete
    0.35
    이너
    0.35
     enlarged
    0.34
     ye
    0.34
     Settlements
    0.33
     Detail
    0.32
     till
    0.32
    Activations Density 0.000%

    No Known Activations