© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13399
    Prev
    Next
    INDEX
    Explanations

    launching new projects or initiatives

    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_13_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
    o
    0.62
    at
    0.59
     restricting
    0.59
    رسٹ
    0.57
    minutes
    0.55
    oof
    0.55
    idges
    0.55
     dvara
    0.54
    vertices
    0.54
    posizione
    0.54
    POSITIVE LOGITS
    تي
    0.57
    يمة
    0.56
    攻撃
    0.56
    циа
    0.55
    toBe
    0.55
    ě
    0.53
    تع
    0.53
    타
    0.53
    チ
    0.52
    生物
    0.52
    Activations Density 0.004%

    No Known Activations