© 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. 86024
    Prev
    Next
    INDEX
    Explanations

    SciFinder, River, Pokémon forms

    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
    hers
    0.75
    that
    0.73
    have
    0.73
    <h2>
    0.71
    houses
    0.69
     i
    0.68
    0.67
    was
    0.66
    had
    0.65
    ته
    0.64
    POSITIVE LOGITS
    ت
    1.27
    an
    1.12
    ed
    1.08
    <0x80>
    1.07
    ing
    1.07
    ת
    1.06
    ும்
    0.96
    ین
    0.87
    t
    0.87
    _
    0.85
    Activations Density 0.001%

    No Known Activations