© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176104
    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_20_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
     pediatric
    0.44
    -
    0.42
    :
    0.41
     distributor
    0.40
     pren
    0.40
     Are
    0.40
     Thanksgiving
    0.40
     beginner
    0.40
     PBS
    0.39
     It
    0.39
    POSITIVE LOGITS
    lbrakk
    0.59
    чиго
    0.56
    Ка
    0.56
     കൂടുതല്‍
    0.52
    కాలు
    0.52
     காரங்கள்
    0.52
    axies
    0.52
     加
    0.52
     vadd
    0.51
    𝗄
    0.51
    Activations Density 0.000%

    No Known Activations