© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198001
    Prev
    Next
    INDEX
    Explanations

    Eric

    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_50_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
    TEMP
    0.39
    Bond
    0.38
    ()->
    0.37
     Bond
    0.37
    Fri
    0.37
     BOND
    0.36
    ()*
    0.36
    TEM
    0.36
     refroid
    0.35
    gini
    0.35
    POSITIVE LOGITS
     carried
    0.44
    詁
    0.43
     Playlist
    0.43
    ρων
    0.42
    クセ
    0.40
     Euler
    0.40
     Heather
    0.39
     Wrestling
    0.39
    کھوں
    0.39
    쭐
    0.39
    Activations Density 0.000%

    No Known Activations