Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 261799
    Prev
    Next
    INDEX
    Explanations

    unistd.h include

    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_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
     které
    1.27
    ंना
    1.23
     thiab
    1.08
    ية
    1.05
     ktoré
    1.03
    ו
    1.02
     který
    1.01
     defunct
    0.99
     varietà
    0.98
     mãos
    0.97
    POSITIVE LOGITS
    a
    1.52
    n
    1.41
    an
    1.38
    د
    1.30
    as
    1.28
    land
    1.24
    up
    1.22
    p
    1.22
    one
    1.19
    d
    1.19
    Activations Density 0.000%

    No Known Activations