© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64265
    Prev
    Next
    INDEX
    Explanations

    say "them" or "those"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    plr
    0.40
     CONTRIBUTION
    0.39
    Parent
    0.38
    lr
    0.37
     comen
    0.36
    矣
    0.36
     contributions
    0.35
     ؛
    0.35
    urably
    0.35
    oper
    0.35
    POSITIVE LOGITS
    them
    0.67
     them
    0.56
     Them
    0.56
    它们
    0.47
     них
    0.45
     THEM
    0.45
    它們
    0.43
     இவற்றை
    0.41
    ющихся
    0.39
    щими
    0.39
    Activations Density 0.019%

    No Known Activations