© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17753
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_40_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
    秫
    0.43
    बैंड
    0.43
    ancourt
    0.40
    ವಾರು
    0.39
    ocolate
    0.39
    зино
    0.39
    ঞ্চলের
    0.38
    nickel
    0.38
    㭂
    0.38
    ജീവ
    0.37
    POSITIVE LOGITS
     смы
    0.41
     உற்ப
    0.37
     முடிந்த
    0.36
    playback
    0.35
     smallest
    0.34
     -
    0.34
    </s>
    0.34
     повто
    0.33
     outlay
    0.33
    smallest
    0.33
    Activations Density 0.028%

    No Known Activations