© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214804
    Prev
    Next
    INDEX
    Explanations

    labels and addresses

    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_50_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
     mercure
    0.43
     winch
    0.41
    忘
    0.40
    OBER
    0.40
    ठान
    0.40
    rafpunkte
    0.39
    Accent
    0.38
     wget
    0.38
     Mercury
    0.38
    Oxford
    0.37
    POSITIVE LOGITS
    (")
    0.43
    coa
    0.40
    ")}
    0.40
    കാശ
    0.38
    Eo
    0.37
    {``
    0.36
     Gio
    0.36
    Gio
    0.36
     filo
    0.36
    рованной
    0.36
    Activations Density 0.000%

    No Known Activations