© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133705
    Prev
    Next
    INDEX
    Explanations

    MHz

    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_1_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
    し
    1.43
    ך
    1.20
    ία
    1.18
    ো
    1.14
    ل
    1.09
    یدار
    1.05
    ئی
    1.03
    ائی
    1.02
    ї
    1.02
    αν
    1.01
    POSITIVE LOGITS
     a
    1.34
    '
    1.20
     كه
    1.16
    ف
    1.15
    w
    1.11
    ח
    1.09
     وي
    1.06
    ו
    1.06
    يق
    1.02
    راك
    1.02
    Activations Density 0.001%

    No Known Activations