© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45422
    Prev
    Next
    INDEX
    Explanations

    DQN, dquote

    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_3_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
    ’),
    0.82
    ر
    0.80
    ク
    0.76
    ション
    0.71
    ’).
    0.71
    ⃙
    0.70
    vén
    0.69
    جين
    0.69
     was
    0.68
    মনসিংহ
    0.68
    POSITIVE LOGITS
    .
    1.27
    f
    0.93
    ab
    0.89
    I
    0.89
    h
    0.87
    ip
    0.79
    g
    0.79
    w
    0.78
    ar
    0.78
    ur
    0.74
    Activations Density 0.004%

    No Known Activations