© 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. 39264
    Prev
    Next
    INDEX
    Explanations

    phone case and bill

    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
    л
    0.90
    и
    0.76
    ل
    0.75
    ер
    0.70
    ので
    0.70
    ạ
    0.67
    і
    0.67
    ус
    0.65
    L
    0.65
    з
    0.65
    POSITIVE LOGITS
    2
    0.72
    0.62
    ka
    0.61
    Nums
    0.60
    sk
    0.58
    the
    0.57
    Code
    0.57
    Sections
    0.55
    ج
    0.55
    0
    0.55
    Activations Density 0.024%

    No Known Activations