© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33485
    Prev
    Next
    INDEX
    Explanations

    claims and rumors

    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_31_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
    Freedom
    0.40
     Freedom
    0.39
     দফা
    0.38
     CENTER
    0.37
     சுதந்திர
    0.37
    ﾒ
    0.36
     criticizing
    0.35
    ająca
    0.35
    瓴
    0.35
     آزادی
    0.34
    POSITIVE LOGITS
     corrupt
    0.32
     rescu
    0.32
     excitement
    0.32
    fib
    0.31
    pé
    0.31
     demolition
    0.31
     indebtedness
    0.30
     disb
    0.30
    펄
    0.30
     jit
    0.29
    Activations Density 0.000%

    No Known Activations