© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77383
    Prev
    Next
    INDEX
    Explanations

    code closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ittä
    0.40
     Това
    0.35
     خالی
    0.35
     بە
    0.34
     থাম
    0.34
     benzyl
    0.33
     قالت
    0.33
    듐
    0.32
     اث
    0.32
     ফরিদ
    0.32
    POSITIVE LOGITS
     studied
    0.43
     objected
    0.40
     objection
    0.40
     doesn
    0.38
     appreciates
    0.38
     Mindfulness
    0.38
    LOCATION
    0.38
    arbeitet
    0.38
     strives
    0.38
     quién
    0.38
    Activations Density 0.006%

    No Known Activations