© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92394
    Prev
    Next
    INDEX
    Explanations

    false alarm rate

    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_11_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
     рэгістра
    0.60
     Reliability
    0.59
    ですが
    0.59
     음
    0.59
     Solubility
    0.57
     Bhan
    0.56
     (“
    0.55
    スメ
    0.55
     textvariable
    0.55
    き
    0.55
    POSITIVE LOGITS
    in
    0.59
    0.59
    你
    0.58
    al
    0.57
     considerate
    0.55
    lot
    0.53
    fest
    0.52
     đốt
    0.52
    election
    0.52
    life
    0.51
    Activations Density 0.001%

    No Known Activations