© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40178
    Prev
    Next
    INDEX
    Explanations

    import, let, /

    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_11_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
    U
    0.97
    H
    0.95
    B
    0.91
    ON
    0.85
    Q
    0.80
    В
    0.80
    Б
    0.79
    On
    0.78
    V
    0.75
    0
    0.75
    POSITIVE LOGITS
    eyim
    0.69
    bibinfo
    0.66
     tastefully
    0.62
     pampered
    0.62
    𝙮
    0.61
     hochwert
    0.57
     herzlich
    0.57
     diffuse
    0.56
     మంచి
    0.56
    
    0.55
    Activations Density 0.019%

    No Known Activations