© 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. 145483
    Prev
    Next
    INDEX
    Explanations

    expressing liking or preference

    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
    ט
    1.52
     to
    1.45
    中
    1.45
     ocen
    1.44
    ை
    1.43
     nač
    1.36
     e
    1.35
     do
    1.34
     and
    1.33
     audit
    1.30
    POSITIVE LOGITS
    l
    1.59
    ت
    1.59
    (
    1.34
    orer
    1.27
    S
    1.23
    ot
    1.21
     of
    1.18
    ert
    1.18
    spiration
    1.17
    othe
    1.16
    Activations Density 0.001%

    No Known Activations