© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 203418
    Prev
    Next
    INDEX
    Explanations

    SAS

    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
    י
    1.51
    ي
    1.50
    i
    1.38
    يلا
    1.19
    ينا
    1.18
     nouvel
    1.09
    。
    1.09
    ে
    1.04
    ।
    1.03
    ი
    1.02
    POSITIVE LOGITS
    g
    1.59
    ll
    1.38
     as
    1.35
    t
    1.30
    на
    1.10
     on
    1.06
    p
    1.06
    ng
    1.00
    v
    1.00
     are
    0.98
    Activations Density 0.000%

    No Known Activations