© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159371
    Prev
    Next
    INDEX
    Explanations

    non-

    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_2_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
    c
    1.64
    d
    1.59
    t
    1.54
    al
    1.50
    s
    1.43
    g
    1.32
    ak
    1.30
     in
    1.28
    b
    1.22
    y
    1.19
    POSITIVE LOGITS
    ного
    1.63
    ное
    1.56
    ни
    1.34
    ación
    1.27
    ку
    1.27
     facilitar
    1.09
    íamos
    1.08
    ную
    1.06
    ность
    1.05
     circunstancias
    1.05
    Activations Density 0.000%

    No Known Activations