© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202391
    Prev
    Next
    INDEX
    Explanations

    air of

    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_6_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
    t
    1.65
    _
    1.28
    l
    1.20
    saus
    1.17
    nd
    1.13
    tal
    1.06
    ne
    1.05
    ng
    1.03
    sp
    1.03
    naire
    1.02
    POSITIVE LOGITS
     në
    1.02
    定め
    1.02
     فی
    1.01
     کۆ
    1.01
     în
    0.98
     کی
    0.98
     لی
    0.96
     ñ
    0.95
     là
    0.95
    0.95
    Activations Density 0.000%

    No Known Activations