© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238290
    Prev
    Next
    INDEX
    Explanations

    film festivals and award winners

    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_25_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
    鳄
    0.40
    ressor
    0.38
     bzw
    0.38
     accessing
    0.37
    টিত
    0.37
     voire
    0.36
     cartão
    0.36
     গণ্য
    0.35
     reschedule
    0.35
     senso
    0.35
    POSITIVE LOGITS
     stoichi
    0.37
    Berkeley
    0.36
    slideClass
    0.34
    umboldt
    0.34
    雹
    0.33
     emigrated
    0.33
     stoichiometry
    0.33
    ʼ
    0.33
    襁
    0.33
     esist
    0.32
    Activations Density 0.000%

    No Known Activations