© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37828
    Prev
    Next
    INDEX
    Explanations

    say "azing"

    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_57_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
     нашей
    0.37
    ர்களை
    0.37
     تضم
    0.36
     жовт
    0.34
    ConfigSource
    0.33
     Brushed
    0.33
    nato
    0.33
    藻
    0.33
     Aku
    0.33
    ですよね
    0.32
    POSITIVE LOGITS
    RAP
    0.47
    layan
    0.43
    lare
    0.42
    lazy
    0.41
     finger
    0.40
    ラ
    0.39
    lac
    0.38
    azed
    0.38
     RAP
    0.38
     lax
    0.38
    Activations Density 0.000%

    No Known Activations