© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65789
    Prev
    Next
    INDEX
    Explanations

    tweets

    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_46_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
     awaits
    0.37
    मंत्र
    0.36
    стар
    0.36
    をする
    0.36
     Concurrent
    0.35
    ♭
    0.34
    ять
    0.34
    닮
    0.34
     verte
    0.33
     impoverished
    0.33
    POSITIVE LOGITS
    Phen
    0.43
     Patria
    0.42
     засто
    0.40
     flex
    0.39
     rekord
    0.38
    Record
    0.38
    可用
    0.38
     aplicando
    0.38
    prf
    0.38
    Flex
    0.38
    Activations Density 0.001%

    No Known Activations