© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18125
    Prev
    Next
    INDEX
    Explanations

    code parsing errors

    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_34_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
     Principles
    0.37
     arcu
    0.36
     kantor
    0.36
    ɬ
    0.35
     entropy
    0.35
     principi
    0.34
     subjected
    0.34
     Pressure
    0.34
     Entropy
    0.34
     exercícios
    0.34
    POSITIVE LOGITS
     言っ
    0.38
     накопи
    0.38
    阱
    0.36
    νε
    0.36
    ͋
    0.36
    ̒
    0.35
     терапии
    0.35
    /'
    0.35
    іо
    0.35
    getCell
    0.34
    Activations Density 0.000%

    No Known Activations