© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4791
    Prev
    Next
    INDEX
    Explanations

    instructions

    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_39_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
     disclosing
    0.42
    cking
    0.39
    лити
    0.38
     consensus
    0.37
    itto
    0.37
    埔
    0.37
     exclus
    0.36
    橘
    0.36
     discretion
    0.36
     disclosed
    0.36
    POSITIVE LOGITS
     príp
    0.39
     />';
    0.39
     instructions
    0.39
    дзі
    0.39
    Instructions
    0.38
    inki
    0.38
     luminance
    0.38
     প্রণ
    0.38
    imagem
    0.37
    instructions
    0.37
    Activations Density 0.038%

    No Known Activations