© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183244
    Prev
    Next
    INDEX
    Explanations

    location and its proximity

    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_29_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
    出一个
    0.44
     சொந்த
    0.42
     autó
    0.40
    ন্দে
    0.39
     ഒരു
    0.39
    }((
    0.38
    一个小
    0.38
     చిన్న
    0.38
    閇
    0.38
     간단
    0.38
    POSITIVE LOGITS
    izarse
    0.38
     Lakes
    0.36
     Russo
    0.36
     Teacher
    0.35
    over
    0.35
    νες
    0.35
    nh
    0.35
     Intelligence
    0.34
    ära
    0.34
     OVER
    0.34
    Activations Density 0.000%

    No Known Activations