© 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. 89052
    Prev
    Next
    INDEX
    Explanations

    order status updates

    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_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
     تصير
    0.41
    ▬▬
    0.40
     напи
    0.40
    layered
    0.38
     SEM
    0.38
     Draw
    0.37
     সন্তানদের
    0.36
     voluptas
    0.36
     siempre
    0.36
    Southeast
    0.36
    POSITIVE LOGITS
    ໃ
    0.39
     enum
    0.38
    ernum
    0.38
    Enum
    0.38
     Enum
    0.36
     заход
    0.36
    did
    0.36
    玫
    0.36
     STATUS
    0.35
    ProductID
    0.35
    Activations Density 0.003%

    No Known Activations