© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82887
    Prev
    Next
    INDEX
    Explanations

    stigmata of

    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_0_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
    a
    1.63
    x
    1.59
    '
    1.57
    k
    1.56
    า
    1.34
    '},
    1.29
    amı
    1.29
    "},
    1.28
    માં
    1.27
     minden
    1.23
    POSITIVE LOGITS
    ன்
    1.55
    ل
    1.41
    نا
    1.26
    <0xB9>
    1.23
    apping
    1.23
    ↵
    1.23
     synthes
    1.20
    لای
    1.18
    ιν
    1.16
    dür
    1.15
    Activations Density 0.000%

    No Known Activations