© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61400
    Prev
    Next
    INDEX
    Explanations

    invitation/announcement

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     come
    0.86
     Come
    0.82
     COME
    0.81
    Come
    0.75
    come
    0.70
    COME
    0.55
    来
    0.50
     Comes
    0.47
    來
    0.47
     comes
    0.44
    POSITIVE LOGITS
     這
    0.53
     fun
    0.52
    Fun
    0.50
    fun
    0.48
     IT
    0.46
    ar
    0.44
    it
    0.43
    It
    0.42
     AML
    0.42
     infix
    0.42
    Activations Density 0.001%

    No Known Activations