© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53810
    Prev
    Next
    INDEX
    Explanations

    how to deal with

    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_30_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
     niektor
    0.39
    ട്ടെ
    0.37
    CONTIN
    0.36
     शायद
    0.35
     야
    0.35
     probabilmente
    0.35
    辆
    0.34
     समापन
    0.34
    脸
    0.34
     ماسکو
    0.34
    POSITIVE LOGITS
    oise
    0.40
    ibb
    0.39
    "><?=$
    0.39
    apd
    0.36
    endige
    0.36
    ஜீ
    0.36
     tempting
    0.35
    dept
    0.35
    কত
    0.35
    qué
    0.35
    Activations Density 0.000%

    No Known Activations