© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111793
    Prev
    Next
    INDEX
    Explanations

    website suffixes .com .org

    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_2_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
    n
    1.27
    <0x80>
    1.11
    s
    1.02
    ры
    1.01
    t
    1.01
    ం
    1.00
    <0x93>
    0.98
    त
    0.98
    <0x95>
    0.96
    ),
    0.94
    POSITIVE LOGITS
     in
    1.13
    ના
    0.94
    .
    0.88
    ア
    0.85
    ム
    0.84
     domínio
    0.82
     Princ
    0.82
    ită
    0.81
    imizi
    0.80
    us
    0.79
    Activations Density 0.003%

    No Known Activations