© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31739
    Prev
    Next
    INDEX
    Explanations

    Namecheap

    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
    ش
    1.36
     has
    1.34
    ک
    1.31
    of
    1.26
     for
    1.23
     improves
    1.19
    s
    1.19
     can
    1.16
    ب
    1.16
    x
    1.14
    POSITIVE LOGITS
    -
    1.02
    I
    0.86
    :
    0.83
    ierung
    0.82
    maßen
    0.78
    痘
    0.78
    ".
    0.77
    乃至
    0.76
    ，
    0.74
    \
    0.71
    Activations Density 0.001%

    No Known Activations