© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145533
    Prev
    Next
    INDEX
    Explanations

    Hatha Yoga, Paratha, Agatha Christie

    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_0_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
    с
    1.55
     are
    1.48
    л
    1.47
     and
    1.38
    ية
    1.38
    ва
    1.37
    water
    1.37
     as
    1.36
    ado
    1.36
    ہ
    1.29
    POSITIVE LOGITS
    ため
    1.40
    ت
    1.40
    "
    1.38
    在
    1.37
    ために
    1.35
     defibr
    1.30
    <0x0D>
    1.30
     hija
    1.25
    am
    1.23
     negras
    1.22
    Activations Density 0.000%

    No Known Activations