© 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. 64635
    Prev
    Next
    INDEX
    Explanations

    flag

    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
    χι
    0.43
     बौ
    0.39
    休
    0.36
     মাত
    0.35
     melon
    0.35
     guer
    0.34
    呟
    0.34
     নৈ
    0.33
    ibers
    0.33
     ustal
    0.33
    POSITIVE LOGITS
     flag
    3.66
     Flag
    3.53
    Flag
    3.47
    flag
    3.41
     flags
    3.31
     Flags
    3.16
     FLAG
    3.09
    flags
    3.02
    Flags
    2.98
    旗
    2.94
    Activations Density 0.005%

    No Known Activations