© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202665
    Prev
    Next
    INDEX
    Explanations

    IFT, CT, VT, FT abbreviations

    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_6_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
    අ
    0.93
    nur
    0.84
    Câu
    0.83
    names
    0.82
    Bookmarks
    0.82
    akers
    0.81
    a
    0.80
    arı
    0.79
    nym
    0.79
    i
    0.79
    POSITIVE LOGITS
    л
    1.23
    ні
    1.16
    ו
    1.16
    та
    1.08
    ם
    1.01
    บ
    0.99
    й
    0.97
    ש
    0.96
    йда
    0.96
    ן
    0.95
    Activations Density 0.000%

    No Known Activations