© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37972
    Prev
    Next
    INDEX
    Explanations

    webgl

    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
    i
    1.59
    ي
    1.13
    ে
    1.03
    י
    1.03
    at
    1.00
    e
    0.98
    an
    0.92
    j
    0.91
    ного
    0.91
    ið
    0.89
    POSITIVE LOGITS
    atico
    0.70
     фі
    0.69
     conduite
    0.68
     ciências
    0.68
    ᱔
    0.67
     on
    0.66
     televisión
    0.64
    щата
    0.63
    ᱕
    0.63
     integración
    0.62
    Activations Density 0.001%

    No Known Activations