© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214289
    Prev
    Next
    INDEX
    Explanations

    staff

    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_5_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
    ad
    1.64
    ut
    1.55
    ہ
    1.48
    ک
    1.40
    f
    1.35
    ate
    1.30
    us
    1.26
    ab
    1.23
    ok
    1.23
    p
    1.18
    POSITIVE LOGITS
    ↵
    1.45
     an
    1.01
    是
    1.01
    <0x98>
    0.98
     É
    0.98
     Kiev
    0.98
     在
    0.96
     我们
    0.90
     Á
    0.89
     функция
    0.89
    Activations Density 0.002%

    No Known Activations