© 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. 34808
    Prev
    Next
    INDEX
    Explanations

    dialogue tags

    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
    綺麗
    0.38
    ]+\
    0.37
    綺麗な
    0.37
    ศี
    0.36
    充滿
    0.36
     पिछड़ा
    0.36
    ۟
    0.34
     ভারসাম
    0.34
     Reconciliation
    0.33
     incompre
    0.33
    POSITIVE LOGITS
     승
    0.40
     subjekt
    0.38
    Td
    0.38
     thắng
    0.37
     বিজয়
    0.37
    승
    0.35
    Ap
    0.35
    Esc
    0.35
     ער
    0.35
     орган
    0.34
    Activations Density 0.008%

    No Known Activations