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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261262
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_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
     for
    1.74
    е
    1.48
     to
    1.37
     as
    1.31
     can
    1.31
    ك
    1.28
    ب
    1.16
    IN
    1.12
    𝟎
    1.10
    υ
    1.09
    POSITIVE LOGITS
    ing
    1.09
    ಯೇ
    1.02
    oi
    0.93
    ingos
    0.93
    (
    0.91
    emar
    0.88
    </h2>
    0.86
    UnderTest
    0.86
    ens
    0.85
     Ско
    0.85
    Activations Density 0.000%

    No Known Activations