© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208277
    Prev
    Next
    INDEX
    Explanations

    message box types

    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_20_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
    Trou
    0.47
     Trouble
    0.44
     trouble
    0.40
    another
    0.39
    膻
    0.38
     которого
    0.38
    jaer
    0.38
     energije
    0.38
    valid
    0.37
    trou
    0.37
    POSITIVE LOGITS
    EROS
    0.44
     treasured
    0.41
    ీల
    0.41
     স্টি
    0.41
     erinner
    0.40
     మ
    0.39
     библиоте
    0.39
     カット
    0.39
     Marble
    0.39
     ម
    0.39
    Activations Density 0.001%

    No Known Activations