© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142282
    Prev
    Next
    INDEX
    Explanations

    yet followed by contrasting adjective

    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_0_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
    ン
    1.66
    ن
    1.63
    н
    1.60
     It
    1.43
     it
    1.33
    น
    1.26
    ν
    1.23
    It
    1.17
    τε
    1.13
    া
    1.12
    POSITIVE LOGITS
    ים
    1.88
    s
    1.55
    다
    1.45
    2
    1.41
    на
    1.38
    ari
    1.35
    b
    1.25
    在
    1.25
    x
    1.23
    are
    1.22
    Activations Density 0.003%

    No Known Activations