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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261247
    Prev
    Next
    INDEX
    Explanations

    consistency expert

    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_5_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
    ↵↵
    1.21
    ה
    1.20
     불구하고
    1.19
    an
    1.14
    ي
    1.13
     αρχ
    1.12
     yanı
    1.09
    i
    1.09
     desenvolv
    1.07
     ամ
    1.06
    POSITIVE LOGITS
    к
    1.48
    с
    1.40
    ور
    1.32
    were
    1.32
    в
    1.21
    ни
    1.19
    (
    1.18
    ain
    1.16
    ons
    1.16
    مان
    1.13
    Activations Density 0.000%

    No Known Activations