© 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. 216754
    Prev
    Next
    INDEX
    Explanations

    seen God

    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
     Okan
    0.38
     먼
    0.38
     faraway
    0.38
     Ang
    0.37
     Mint
    0.36
     deterior
    0.35
    onent
    0.35
     Idha
    0.35
     kneel
    0.35
     लागू
    0.34
    POSITIVE LOGITS
    Disagree
    0.38
    袬
    0.33
    𝐵
    0.32
    disposing
    0.32
     А
    0.31
    ਕਰ
    0.31
     синд
    0.31
    jsdel
    0.30
     مرت
    0.30
     উঠ
    0.30
    Activations Density 0.000%

    No Known Activations