© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159585
    Prev
    Next
    INDEX
    Explanations

    varies"

    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_2_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
     و
    1.30
    ING
    1.15
    nd
    1.13
    ेट
    1.04
    tä
    0.99
    和
    0.98
     and
    0.93
    িলিয়া
    0.91
    ួក
    0.89
    t
    0.89
    POSITIVE LOGITS
    ור
    2.17
    n
    1.59
    it
    1.55
    an
    1.48
    ى
    1.48
    ir
    1.47
    ou
    1.45
    ר
    1.43
    et
    1.39
    as
    1.38
    Activations Density 0.000%

    No Known Activations