© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231011
    Prev
    Next
    INDEX
    Explanations

    Batch Normalization

    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
    zens
    0.88
    )})
    0.87
     emocion
    0.87
     protrusions
    0.82
    adays
    0.81
     egent
    0.81
     Π
    0.80
    )}\
    0.80
    )}-
    0.80
     Oprah
    0.80
    POSITIVE LOGITS
    at
    1.25
    к
    1.06
    ні
    1.05
    ба
    1.00
    τή
    0.94
    ле
    0.91
    ци
    0.91
    am
    0.89
    、
    0.89
    -
    0.87
    Activations Density 0.000%

    No Known Activations