© 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. 68300
    Prev
    Next
    INDEX
    Explanations

    say "<"

    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
    >${
    0.36
     متاثر
    0.36
    сион
    0.34
    stieg
    0.34
    釦
    0.34
    iber
    0.33
    ズム
    0.33
    onces
    0.33
    ibilidades
    0.33
    ém
    0.32
    POSITIVE LOGITS
     Single
    0.56
    Single
    0.55
    單
    0.49
     single
    0.47
    单
    0.45
    निव
    0.45
    single
    0.44
     đơn
    0.43
     Polyp
    0.41
    単
    0.40
    Activations Density 0.002%

    No Known Activations