© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22626
    Prev
    Next
    INDEX
    Explanations

    even or odd

    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_56_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
     odd
    2.59
     Odd
    2.23
    Odd
    2.20
    odd
    2.06
    奇
    1.74
     weird
    1.56
     strange
    1.55
     стран
    1.39
     Weird
    1.33
    weird
    1.32
    POSITIVE LOGITS
     wer
    0.61
     WER
    0.51
    Wer
    0.49
    wer
    0.45
     WE
    0.45
    WER
    0.42
     Wer
    0.42
     desech
    0.38
    ⎮
    0.37
     wl
    0.37
    Activations Density 0.064%

    No Known Activations