© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158032
    Prev
    Next
    INDEX
    Explanations

    воздушной тревоге

    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
    a
    1.77
    is
    1.47
    y
    1.34
    ה
    1.33
     was
    1.32
    at
    1.30
    n
    1.24
    -
    1.20
    an
    1.18
    ם
    1.17
    POSITIVE LOGITS
    д
    1.09
     étoiles
    1.05
    lø
    1.04
     antérieurs
    1.03
    ل
    1.02
    leri
    1.01
    )。
    1.00
     använd
    0.99
     oktober
    0.98
    lere
    0.98
    Activations Density 0.000%

    No Known Activations