© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33890
    Prev
    Next
    INDEX
    Explanations

    Studies have shown

    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
     remastered
    0.71
     heavyweight
    0.68
     }^{+}$
    0.67
    вається
    0.66
     categor
    0.66
    springframework
    0.64
     reeling
    0.64
    ۰۰
    0.64
     transmis
    0.63
     impasse
    0.63
    POSITIVE LOGITS
     jede
    0.89
    o
    0.74
    وم
    0.73
    FAULT
    0.73
    ol
    0.72
    Ƒ
    0.72
    AZ
    0.71
    y
    0.71
    PORT
    0.70
    DON
    0.70
    Activations Density 0.004%

    No Known Activations