© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50723
    Prev
    Next
    INDEX
    Explanations

    a

    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_55_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
     qualifications
    0.41
    短
    0.39
    φή
    0.38
     Short
    0.37
    Short
    0.37
     корот
    0.37
    நர்
    0.37
    Active
    0.36
     short
    0.35
    뭍
    0.35
    POSITIVE LOGITS
     very
    0.69
    very
    0.64
     sehr
    0.63
    VERY
    0.61
     дуже
    0.59
     bardzo
    0.58
     meget
    0.58
     VERY
    0.58
     очень
    0.57
    非常に
    0.57
    Activations Density 0.019%

    No Known Activations