© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78333
    Prev
    Next
    INDEX
    Explanations

    Unreal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    iers
    0.40
     ==
    0.37
    illons
    0.37
     ether
    0.37
     ethernet
    0.37
    宣
    0.36
    กรม
    0.35
     жена
    0.35
     مني
    0.35
     uts
    0.34
    POSITIVE LOGITS
    ডিং
    0.42
     Dob
    0.38
    ابہ
    0.38
    ༽
    0.38
    tabPadding
    0.37
    ভিং
    0.37
     reali
    0.37
     بڑے
    0.37
    ہا
    0.36
    𝖗
    0.36
    Activations Density 0.001%

    No Known Activations