© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145832
    Prev
    Next
    INDEX
    Explanations

    say place names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     pocas
    0.50
     pocos
    0.44
    edRight
    0.42
     Decedent
    0.42
     few
    0.41
    ཚ
    0.40
    few
    0.39
     poucos
    0.39
    )));
    0.38
     Hef
    0.37
    POSITIVE LOGITS
     UNITED
    0.49
     Philippines
    0.47
     인도
    0.47
     her
    0.45
    インド
    0.45
     florida
    0.44
     Bharatiya
    0.44
    court
    0.42
     philippines
    0.42
     FLORIDA
    0.42
    Activations Density 0.001%

    No Known Activations