© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39323
    Prev
    Next
    INDEX
    Explanations

    test system setup

    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_3_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
    RO
    0.71
    att
    0.67
    orn
    0.60
    ä
    0.60
    any
    0.59
    əl
    0.59
    är
    0.57
    ă
    0.57
    ED
    0.57
    ig
    0.56
    POSITIVE LOGITS
    т
    0.72
    0.72
    ли
    0.70
    ፩
    0.65
     criminally
    0.64
    (),
    0.64
    ﺭ
    0.63
    ্ট
    0.63
    t
    0.63
    ৬
    0.63
    Activations Density 0.014%

    No Known Activations