© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200217
    Prev
    Next
    INDEX
    Explanations

    tapeworm segments, eggs, head

    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_12_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
    preserve
    0.54
     bakan
    0.52
    s
    0.52
    衫
    0.51
    Probability
    0.50
    )$
    0.49
    traf
    0.49
    treasure
    0.47
     méthodique
    0.47
    ）
    0.46
    POSITIVE LOGITS
     com
    0.58
     मिळाल
    0.49
     Futures
    0.48
     fut
    0.48
     стек
    0.47
     asm
    0.47
     havde
    0.46
     wheelchairs
    0.46
     τη
    0.46
     comed
    0.46
    Activations Density 0.000%

    No Known Activations