© 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. 160143
    Prev
    Next
    INDEX
    Explanations

    suffix -ic, -ics, -ix

    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
    (
    1.23
    (())
    1.00
    1
    0.95
    ideo
    0.91
    iga
    0.90
    9
    0.90
    ite
    0.86
    8
    0.86
    맇
    0.86
     बिक्री
    0.83
    POSITIVE LOGITS
    d
    1.62
    я
    1.38
    し
    1.24
    m
    1.18
    ش
    1.17
    ма
    1.13
    на
    1.12
    س
    1.11
    ↵↵
    1.09
    в
    1.08
    Activations Density 0.001%

    No Known Activations