© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37854
    Prev
    Next
    INDEX
    Explanations

    set something up

    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
    usual
    0.38
    ｌ
    0.37
    uation
    0.37
    eyes
    0.35
    基因
    0.35
    only
    0.34
    interesting
    0.33
    पेक्ष
    0.33
    up
    0.33
    ulations
    0.33
    POSITIVE LOGITS
    ]
    0.38
    ;*/
    0.36
     advocate
    0.35
     =
    0.35
     violated
    0.34
     porch
    0.34
     wrongfully
    0.34
     impart
    0.33
     invert
    0.33
     $$
    0.32
    Activations Density 0.013%

    No Known Activations