© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91349
    Prev
    Next
    INDEX
    Explanations

    form, __disease, foundation, __sweep

    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_3_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
    מ
    0.70
    ين
    0.68
    lll
    0.66
    هم
    0.65
    tt
    0.64
    ני
    0.62
    לי
    0.60
    لي
    0.59
    c
    0.59
    j
    0.59
    POSITIVE LOGITS
     in
    0.77
     в
    0.64
    нить
    0.62
    ość
    0.60
    €™
    0.59
            
    0.58
     ¹
    0.58
    麺
    0.55
     are
    0.55
     composing
    0.54
    Activations Density 0.042%

    No Known Activations