© 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. 210320
    Prev
    Next
    INDEX
    Explanations

    couplets

    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
     მაგრამ
    0.90
    ið
    0.88
    iéndose
    0.85
     comple
    0.84
    ת
    0.84
    avasena
    0.83
     provoqu
    0.83
     அமைந்துள்ளது
    0.82
     финансо
    0.81
     electrón
    0.81
    POSITIVE LOGITS
    s
    1.18
    sl
    1.14
    q
    1.14
     for
    1.02
     It
    1.02
     I
    1.00
     be
    0.99
    "]
    0.99
    .}
    0.99
    <0x0D>
    0.98
    Activations Density 0.000%

    No Known Activations