© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44277
    Prev
    Next
    INDEX
    Explanations

    market drivers and trends

    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_22_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
    ût
    0.44
    typography
    0.42
     listopada
    0.40
    壬
    0.38
     mLocation
    0.38
    ҳ
    0.38
    јо
    0.37
    ғ
    0.37
     run
    0.37
     –
    0.37
    POSITIVE LOGITS
     aberrations
    0.47
     steampunk
    0.45
    स्तानी
    0.44
     luscious
    0.44
    kennt
    0.41
     idios
    0.41
     whimsical
    0.41
     thermometer
    0.40
    フィール
    0.40
     crevices
    0.40
    Activations Density 0.000%

    No Known Activations