© 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. 30819
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    RFID
    0.41
    Tes
    0.41
     patiently
    0.39
    Alive
    0.39
    ㄚ
    0.39
     Daven
    0.38
    weight
    0.38
    フード
    0.38
    Will
    0.37
    Weight
    0.37
    POSITIVE LOGITS
     Hometown
    0.38
     enh
    0.37
     горо
    0.35
     erhö
    0.34
     ١
    0.34
     mnemonic
    0.34
    离婚
    0.34
    阴
    0.34
     foreach
    0.34
     enhanced
    0.33
    Activations Density 0.000%

    No Known Activations