© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5388
    Prev
    Next
    INDEX
    Explanations

    championships and longevity

    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_39_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
    荘
    0.36
    qv
    0.36
     Hire
    0.36
     NT
    0.35
    Ty
    0.35
     σχ
    0.35
    Hire
    0.35
    opened
    0.34
     Rouse
    0.34
    मणि
    0.34
    POSITIVE LOGITS
    伌
    0.42
     Finals
    0.41
     asphy
    0.37
     finals
    0.37
    менты
    0.37
     Coupon
    0.36
     silverware
    0.36
     consistency
    0.35
     сере
    0.35
     sevi
    0.35
    Activations Density 0.031%

    No Known Activations