© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89743
    Prev
    Next
    INDEX
    Explanations

    relates to

    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_3_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
    0.82
    は大
    0.73
    ン
    0.71
    IND
    0.68
     powied
    0.67
     iniziato
    0.64
     הראש
    0.64
     accel
    0.61
    н
    0.60
     shouldn
    0.59
    POSITIVE LOGITS
    k
    0.77
    kring
    0.73
    نه
    0.71
    kaya
    0.71
    ко
    0.68
     lockdowns
    0.68
    á
    0.66
    dienst
    0.66
    z
    0.66
    не
    0.65
    Activations Density 0.004%

    No Known Activations