© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234462
    Prev
    Next
    INDEX
    Explanations

    to be verbs

    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
     ट्रांसपोर्ट
    0.46
     پذیر
    0.41
    transport
    0.40
    毓
    0.38
    也很
    0.37
    লন
    0.37
    ườn
    0.37
     rất
    0.37
     renvers
    0.37
    很
    0.37
    POSITIVE LOGITS
     hol
    0.42
     hind
    0.39
     vows
    0.38
     LEP
    0.37
     filed
    0.37
     suivent
    0.36
     crossed
    0.36
    eland
    0.35
     Dal
    0.35
     directional
    0.34
    Activations Density 0.001%

    No Known Activations