© 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. 143389
    Prev
    Next
    INDEX
    Explanations

    indistinct early symptoms or shapes

    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
    是
    1.56
     in
    1.54
    k
    1.43
    ing
    1.42
    c
    1.39
     as
    1.38
     on
    1.34
    л
    1.30
    这
    1.29
     أ
    1.21
    POSITIVE LOGITS
    )
    1.56
    <0x80>
    1.27
    ),
    1.23
     pavattati
    1.09
    ้น
    1.03
    ਰ
    1.03
    ugan
    1.02
    ),]),
    1.01
     qualific
    1.00
    ி
    1.00
    Activations Density 0.000%

    No Known Activations