© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201391
    Prev
    Next
    INDEX
    Explanations

    Blazor Server

    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_6_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
    ı
    0.91
    ’
    0.87
    '
    0.80
     comune
    0.76
     Chartered
    0.71
     communiqué
    0.71
     squadron
    0.70
    ).
    0.70
     certificat
    0.69
     reconnaître
    0.69
    POSITIVE LOGITS
     to
    1.42
     be
    1.12
    1
    1.11
    스를
    1.07
    s
    1.05
    3
    1.05
    ش
    0.98
    지
    0.98
     cleats
    0.95
    0
    0.95
    Activations Density 0.000%

    No Known Activations