© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202558
    Prev
    Next
    INDEX
    Explanations

    Python dataclasses

    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_46_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
    marshalN
    0.37
    allocated
    0.37
    ীম
    0.37
    PEND
    0.36
    দ
    0.35
     NA
    0.35
    ddot
    0.34
     Guidance
    0.33
     menyel
    0.33
    ⑹
    0.33
    POSITIVE LOGITS
     تغيير
    0.46
     Froome
    0.45
     Camb
    0.42
     Change
    0.41
     বলিয়াছেন
    0.41
    emaker
    0.41
    境界
    0.41
     Lann
    0.41
    ovej
    0.40
     equilibria
    0.40
    Activations Density 0.000%

    No Known Activations