© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205141
    Prev
    Next
    INDEX
    Explanations

    create, craft, build, modify

    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_25_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
    iosk
    0.44
    等着
    0.42
    about
    0.40
    ,“
    0.38
    incar
    0.37
    escence
    0.37
    !“
    0.37
    货
    0.36
    Went
    0.35
    ْ
    0.35
    POSITIVE LOGITS
     tvr
    0.43
     reaffirm
    0.38
     terlalu
    0.37
     없음
    0.37
     unable
    0.36
     sufficient
    0.36
     Ps
    0.35
     otrzym
    0.35
     QQ
    0.35
    を変更
    0.35
    Activations Density 0.016%

    No Known Activations