© 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
    2. Gemma-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 51649
    Prev
    Next
    INDEX
    Explanations

    average calculation

    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
    Weighted
    0.89
    weighted
    0.86
     weighted
    0.83
     Weighted
    0.82
    Minor
    0.40
     llor
    0.38
    晖
    0.37
     sobbing
    0.36
    哭
    0.36
    ̻
    0.35
    POSITIVE LOGITS
     moving
    0.59
     arithmetic
    0.59
     un
    0.55
    arith
    0.51
    Arithmetic
    0.51
     raw
    0.51
     Equally
    0.51
     Arithmetic
    0.50
     equally
    0.49
     Moving
    0.47
    Activations Density 0.080%

    No Known Activations