© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197371
    Prev
    Next
    INDEX
    Explanations

    i-vector, bus, integrate, recommend

    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_4_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
    a
    0.66
    ał
    0.65
    forschung
    0.61
    يد
    0.61
    first
    0.59
    是否有
    0.59
    يها
    0.58
    <0x0D>
    0.57
    fight
    0.57
    জর
    0.57
    POSITIVE LOGITS
     to
    0.69
     It
    0.64
     eagerness
    0.64
     iterates
    0.62
    แส
    0.61
     adenocarcinoma
    0.60
    ری
    0.59
     theses
    0.59
     semangat
    0.58
     때문에
    0.57
    Activations Density 0.000%

    No Known Activations