© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37844
    Prev
    Next
    INDEX
    Explanations

    de followed by text

    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_11_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
    \
    0.86
    </h1>
    0.67
    </h4>
    0.66
    и
    0.65
    지
    0.65
    İ
    0.64
    ні
    0.63
    ని
    0.63
    ِ
    0.61
     -
    0.61
    POSITIVE LOGITS
    asche
    0.58
    ovost
    0.56
    posed
    0.55
     εκ
    0.55
     ρ
    0.55
    туа
    0.55
    oraj
    0.54
    heses
    0.54
    voorbeeld
    0.53
     το
    0.52
    Activations Density 0.000%

    No Known Activations