© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154023
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     Structures
    0.43
    SLE
    0.42
    s
    0.42
    cheap
    0.41
    ME
    0.40
     asleep
    0.39
    minutes
    0.39
    immers
    0.39
     shovel
    0.38
    monton
    0.38
    POSITIVE LOGITS
    лна
    0.54
    廨
    0.53
    ет
    0.51
    ानुसार
    0.50
    KindOfClass
    0.50
    に関
    0.49
    ilung
    0.49
    લ
    0.49
    𝑬
    0.49
    Всім
    0.48
    Activations Density 0.000%

    No Known Activations