© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30870
    Prev
    Next
    INDEX
    Explanations

    multiline text blocks

    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_7_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
     to
    1.13
    0
    1.05
    1
    1.02
    ని
    0.99
    ה
    0.91
    இ
    0.91
    ه
    0.91
    in
    0.90
    '
    0.89
    h
    0.89
    POSITIVE LOGITS
    。
    0.95
     божомол
    0.92
    、
    0.81
    ンの
    0.79
     ラ
    0.79
     також
    0.79
     پہنچ
    0.79
     corroborate
    0.78
     pesto
    0.78
     کریں۔
    0.77
    Activations Density 0.001%

    No Known Activations