© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212800
    Prev
    Next
    INDEX
    Explanations

    whisky brands and age

    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_43_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
     சோ
    0.40
     riddled
    0.39
    ἰ
    0.38
     Civilian
    0.38
    谲
    0.38
     Zel
    0.37
    ව්
    0.37
    ovat
    0.36
     SF
    0.36
     ول
    0.36
    POSITIVE LOGITS
     пошу
    0.40
    쁨
    0.37
    semibold
    0.37
    絕對
    0.37
    鰯
    0.36
     smoke
    0.36
     Francesca
    0.36
    ranos
    0.36
     finishes
    0.35
     ++)
    0.35
    Activations Density 0.001%

    No Known Activations