© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62512
    Prev
    Next
    INDEX
    Explanations

    ~ relation symbol

    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_41_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
     chief
    0.35
     bare
    0.34
     Vanity
    0.34
    chief
    0.34
     Vantage
    0.34
    职
    0.33
    絵
    0.33
     pastor
    0.32
    ेट
    0.32
     unem
    0.32
    POSITIVE LOGITS
     ~
    2.33
     ~.
    2.02
     ~,
    2.02
    ~
    1.96
     ~(
    1.92
     ∼
    1.88
    ～
    1.86
    .~
    1.84
    ~)
    1.84
     ~$
    1.84
    Activations Density 0.002%

    No Known Activations