© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158915
    Prev
    Next
    INDEX
    Explanations

    undefinable

    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
    d
    1.59
    。
    1.33
    dengan
    1.30
    dalam
    1.26
    ד
    1.26
    ।
    1.21
    רו
    1.05
    מ
    0.99
    ג
    0.98
    د
    0.95
    POSITIVE LOGITS
    is
    1.36
    <0x0D>
    1.32
    in
    1.28
    ación
    1.20
    inio
    1.13
    iné
    1.13
    inę
    1.13
    inins
    1.10
    isers
    1.09
     bulunduğu
    1.08
    Activations Density 0.000%

    No Known Activations