© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215467
    Prev
    Next
    INDEX
    Explanations

    product volume

    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_16_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
    位
    0.55
    ās
    0.51
    dem
    0.48
    Admission
    0.47
    etics
    0.45
     नियोजन
    0.44
    smanship
    0.44
    优惠
    0.43
    sy
    0.42
    io
    0.42
    POSITIVE LOGITS
     probleme
    0.48
     與
    0.46
     richtig
    0.45
    後に
    0.45
     problemi
    0.45
    ⸨
    0.45
     branca
    0.45
     دیتی
    0.44
     apari
    0.44
     prostit
    0.43
    Activations Density 0.000%

    No Known Activations