© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43440
    Prev
    Next
    INDEX
    Explanations

    client-side or server-side

    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
    ב
    0.74
    ש
    0.73
    ranial
    0.71
    те
    0.69
     odnosno
    0.68
    ่ง
    0.65
    ндекс
    0.65
    ס
    0.65
    ので
    0.64
    ா
    0.64
    POSITIVE LOGITS
    ing
    0.71
     aproxim
    0.65
    佅
    0.61
    chin
    0.60
    【
    0.60
     substitu
    0.59
    us
    0.59
     It
    0.59
    <h5>
    0.57
    "},
    0.57
    Activations Density 0.035%

    No Known Activations