© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 60086
    Prev
    Next
    INDEX
    Explanations

    Rol followed by words, names, or specific characters

    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
     for
    1.38
    for
    1.35
    n
    1.34
    is
    1.28
     L
    1.27
    at
    1.17
    ר
    1.16
    i
    1.10
    y
    1.08
    ad
    1.06
    POSITIVE LOGITS
    ના
    1.66
    ре
    1.51
    ні
    1.48
    いた
    1.43
    می
    1.43
    ку
    1.34
    ला
    1.33
    리
    1.32
    ری
    1.30
    ك
    1.27
    Activations Density 0.000%

    No Known Activations