© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172973
    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
     δεν
    0.59
    uose
    0.58
    𝗽
    0.52
    ದಲ್ಲಿ
    0.50
     tidak
    0.49
    𝗦
    0.49
    他說
    0.49
     dragged
    0.48
     amounting
    0.47
     ότι
    0.47
    POSITIVE LOGITS
     impressive
    0.53
    0.50
    ark
    0.49
     ARK
    0.46
    ä
    0.43
     Ark
    0.43
     Consistent
    0.42
     ark
    0.41
     Encour
    0.41
     Viewing
    0.41
    Activations Density 0.000%

    No Known Activations