© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106646
    Prev
    Next
    INDEX
    Explanations

    most recent

    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_1_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
     має
    1.06
     meski
    0.99
     estratégia
    0.94
     ३
    0.94
     ее
    0.92
     acceder
    0.92
     Andaman
    0.91
    ająca
    0.91
     fiume
    0.91
     եւ
    0.90
    POSITIVE LOGITS
    ت
    1.59
    _
    1.54
    s
    1.49
    {
    1.41
    5
    1.34
    ।
    1.32
    1
    1.30
    I
    1.26
    ه
    1.26
    .
    1.25
    Activations Density 0.001%

    No Known Activations