© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112704
    Prev
    Next
    INDEX
    Explanations

    back followed by direction or completion

    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_2_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
    0.79
    們
    0.73
    рд
    0.73
    лна
    0.71
    ция
    0.68
     downlink
    0.68
    会不会
    0.66
     chieft
    0.65
     realistically
    0.65
    ът
    0.64
    POSITIVE LOGITS
    n
    1.75
    la
    1.19
    你
    1.10
    ri
    1.09
    de
    1.08
    le
    1.06
    m
    1.03
    ق
    1.03
    ى
    1.01
    nemen
    0.99
    Activations Density 0.003%

    No Known Activations