© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146011
    Prev
    Next
    INDEX
    Explanations

    ade followed by numbers or common suffixes

    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_0_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
     to
    1.89
    ä
    1.83
     on
    1.59
     you
    1.30
     not
    1.20
    وم
    1.19
    ου
    1.11
     y
    1.09
     with
    1.08
     is
    1.07
    POSITIVE LOGITS
    i
    1.84
    2
    1.83
    ي
    1.70
    a
    1.39
    ه
    1.30
    l
    1.25
    ال
    1.24
    ið
    1.23
    يلا
    1.20
    ２
    1.20
    Activations Density 0.000%

    No Known Activations