© 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. 196715
    Prev
    Next
    INDEX
    Explanations

    Sto

    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
    剌
    0.46
    ಿತು
    0.38
     modul
    0.38
    ţional
    0.38
    ದಯ
    0.37
    メンズ
    0.37
     physiologique
    0.37
    ✘
    0.37
     skating
    0.36
    න
    0.36
    POSITIVE LOGITS
    decrease
    0.38
     навча
    0.37
     reduced
    0.36
    opencv
    0.35
    アレ
    0.35
     haq
    0.34
    وار
    0.34
    arriv
    0.34
    கரு
    0.34
     технику
    0.34
    Activations Density 0.000%

    No Known Activations