© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168633
    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_56_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
    neath
    0.41
    CE
    0.37
    時
    0.36
    NewLabel
    0.36
    TagName
    0.35
     cef
    0.35
    OrEqualTo
    0.35
    FO
    0.34
     জন্যই
    0.34
    StreetMap
    0.34
    POSITIVE LOGITS
     czek
    0.41
     기다
    0.39
     Iterable
    0.38
    🔄
    0.38
    мата
    0.38
     interrupting
    0.38
     investing
    0.37
    icae
    0.37
    activating
    0.37
    ycji
    0.37
    Activations Density 0.000%

    No Known Activations