© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79900
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunction

    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_31_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
    One
    0.38
     lecteurs
    0.36
    渦
    0.36
    infoHeader
    0.35
    Population
    0.35
    hiddenMap
    0.35
    Hi
    0.34
    的身
    0.34
    Qualifications
    0.34
    Structural
    0.34
    POSITIVE LOGITS
    깡
    0.39
     집에
    0.37
    ын
    0.37
    =>$
    0.35
    >("
    0.33
     ফটোগ্রাফ
    0.33
     <$>
    0.32
    醀
    0.32
     ["
    0.32
    )^{(
    0.32
    Activations Density 0.007%

    No Known Activations