© 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. 3830
    Prev
    Next
    INDEX
    Explanations

    project path and existing code

    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
    вається
    0.37
    瑕
    0.37
    яз
    0.36
     устойчи
    0.36
    Mail
    0.35
    เน
    0.35
    спеди
    0.35
    BOUNDARY
    0.35
     Esch
    0.35
    <0xB9>
    0.35
    POSITIVE LOGITS
    0.40
    InputChange
    0.39
     forces
    0.38
     Princip
    0.38
     manipulation
    0.38
     Jar
    0.37
     locale
    0.37
     probleml
    0.37
     Į
    0.37
     jars
    0.36
    Activations Density 0.001%

    No Known Activations