© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97092
    Prev
    Next
    INDEX
    Explanations

    leaders and names

    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_14_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
    の発
    0.52
     maliciously
    0.52
     malice
    0.51
    ডিস
    0.50
    訌
    0.50
    to
    0.50
     کان
    0.50
    初の
    0.49
    ड
    0.49
    \]
    0.49
    POSITIVE LOGITS
    ेश्व
    0.52
     वाकई
    0.52
    💆
    0.50
     hechas
    0.49
    homogeneous
    0.49
    Ӣ
    0.49
    hum
    0.48
    tell
    0.48
     Olha
    0.48
    <0xA0>
    0.48
    Activations Density 0.000%

    No Known Activations