© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142944
    Prev
    Next
    INDEX
    Explanations

    Sasanian

    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
    scriptstyle
    0.41
    Markers
    0.39
     اث
    0.38
     composition
    0.38
    槃
    0.38
     diagnosis
    0.37
    arsch
    0.37
    emeinschaft
    0.37
    の記事
    0.37
    לו
    0.36
    POSITIVE LOGITS
     synt
    0.43
    轵
    0.39
    bao
    0.39
     sintet
    0.39
    ड़ाई
    0.38
    ,*/}*.
    0.38
    ilib
    0.37
     desal
    0.37
     difícil
    0.35
    unregister
    0.35
    Activations Density 0.000%

    No Known Activations