© 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. 35423
    Prev
    Next
    INDEX
    Explanations

    journal titles

    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
    Ⲛ
    0.38
     کرسکتے
    0.37
    Will
    0.35
     Will
    0.35
     sebagaimana
    0.33
    能够在
    0.33
    成
    0.32
    Than
    0.32
     graag
    0.32
     রহমান
    0.32
    POSITIVE LOGITS
    ্কৃত
    0.40
     gekommen
    0.39
     doux
    0.38
    ຖື
    0.38
     knocks
    0.37
    醮
    0.36
    女子
    0.35
     knocked
    0.35
    dürü
    0.35
     carrito
    0.35
    Activations Density 0.001%

    No Known Activations