© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134654
    Prev
    Next
    INDEX
    Explanations

    message content

    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_37_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
     newState
    0.36
     Ferrer
    0.36
     Bere
    0.35
    )});
    0.35
     Estado
    0.34
     Genome
    0.34
    cvtColor
    0.34
    ্বস্ত
    0.34
     अवज्ञा
    0.34
     አል
    0.34
    POSITIVE LOGITS
    VideoStream
    0.40
    ╿
    0.36
    ഗീയ
    0.36
    ultan
    0.36
    追踪
    0.36
    kys
    0.36
    controls
    0.36
     Aenean
    0.35
    breadcrumb
    0.35
    ieben
    0.34
    Activations Density 0.000%

    No Known Activations