© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 51994
    Prev
    Next
    INDEX
    Explanations

    less than

    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
    eville
    0.38
    ---|
    0.38
     निघ
    0.38
    ipton
    0.37
     tepl
    0.36
     आधार
    0.36
    த்துடன்
    0.36
     vamp
    0.35
    岔
    0.34
     valign
    0.34
    POSITIVE LOGITS
     lower
    0.47
     Lower
    0.46
    Lower
    0.44
     LOWER
    0.44
     أقل
    0.43
     lowercase
    0.43
    做得
    0.42
     approaches
    0.41
    lower
    0.38
     less
    0.38
    Activations Density 0.000%

    No Known Activations