© 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. 261206
    Prev
    Next
    INDEX
    Explanations

    antithesis, antithetical

    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
    ى
    1.41
    ก
    1.33
    ιν
    1.14
    л
    1.09
     I
    1.05
    ны
    1.02
    та
    1.00
    ld
    1.00
    ння
    0.99
    ും
    0.98
    POSITIVE LOGITS
    ’
    1.32
     is
    1.17
    TA
    1.09
     a
    1.08
    ために
    1.07
    ため
    1.05
    場合は
    1.02
    ע
    1.00
     as
    0.98
     legitim
    0.96
    Activations Density 0.000%

    No Known Activations