© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195707
    Prev
    Next
    INDEX
    Explanations

    Y

    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_50_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
     Ren
    0.50
     ren
    0.49
     REN
    0.46
     VoIP
    0.45
    ቮ
    0.44
     Voltaire
    0.43
     volunteer
    0.43
     кот
    0.42
     Kot
    0.41
    वनि
    0.41
    POSITIVE LOGITS
     Y
    0.62
    Y
    0.57
     y
    0.48
    vest
    0.47
    ests
    0.46
    SRP
    0.46
     य
    0.46
     ਯ
    0.45
    jest
    0.44
     ی
    0.43
    Activations Density 0.003%

    No Known Activations