© 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. 52157
    Prev
    Next
    INDEX
    Explanations

    scientific explanations

    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
     pounds
    0.44
    wherein
    0.40
     phổ
    0.39
     (£
    0.39
     Rocca
    0.38
     libras
    0.38
     pertains
    0.37
     £
    0.37
     Kieran
    0.37
    镑
    0.37
    POSITIVE LOGITS
     fuels
    0.45
    启发
    0.38
    فع
    0.38
     Landing
    0.37
    fuels
    0.37
    '`--
    0.37
    !}
    0.36
    Worked
    0.36
     soils
    0.36
     thresholds
    0.36
    Activations Density 0.002%

    No Known Activations