© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52093
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios

    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_55_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
    ..,
    0.44
     기본
    0.44
    ↓
    0.42
    ⮕
    0.40
     ㅣ
    0.38
    Breaking
    0.38
    基本
    0.38
    OLDER
    0.37
     ~
    0.37
    :{
    0.37
    POSITIVE LOGITS
     scenarios
    0.51
    ?).
    0.46
     fantasies
    0.43
     conjectures
    0.43
     theories
    0.40
    ?");
    0.40
    ?")
    0.40
     reputed
    0.40
    ?}",
    0.40
     tries
    0.39
    Activations Density 0.014%

    No Known Activations