© 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. 200304
    Prev
    Next
    INDEX
    Explanations

    cd command to change directory

    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
     puree
    0.55
    ljed
    0.52
     mailing
    0.52
     powied
    0.48
    mailing
    0.47
     ভরে
    0.46
     frühen
    0.46
    ư
    0.46
    쑹
    0.45
    Kü
    0.45
    POSITIVE LOGITS
    臭
    0.52
     adduced
    0.49
     asfalt
    0.47
    ana
    0.47
    目
    0.46
     essere
    0.45
     anisot
    0.45
     auriculares
    0.45
     decoupled
    0.45
    棘
    0.45
    Activations Density 0.003%

    No Known Activations