© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227321
    Prev
    Next
    INDEX
    Explanations

    i am / i feel / i want

    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_6_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
    c
    1.06
     so
    0.91
    b
    0.90
    يا
    0.88
    an
    0.84
    یث
    0.84
    ای
    0.82
    نی
    0.82
    ă
    0.82
    шими
    0.80
    POSITIVE LOGITS
    。",
    0.95
    。"
    0.95
    ס
    0.94
    oMatrix
    0.89
     заседа
    0.88
    ۔
    0.88
    Af
    0.86
     المنطقة
    0.82
    <unused338>
    0.81
    Á
    0.81
    Activations Density 0.001%

    No Known Activations