© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36838
    Prev
    Next
    INDEX
    Explanations

    ize/ise suffix

    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
    a
    1.48
    t
    1.43
    i
    1.16
    g
    1.05
    u
    1.04
    e
    1.01
    k
    0.91
    c
    0.87
    o
    0.86
    aise
    0.84
    POSITIVE LOGITS
    פ
    1.09
    м
    1.05
    (),
    1.04
    ב
    1.03
    மக்கள்
    1.01
    써
    1.00
    ፤
    0.97
    ва
    0.93
    ین
    0.93
    ند
    0.92
    Activations Density 0.000%

    No Known Activations