© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142719
    Prev
    Next
    INDEX
    Explanations

    RAN acronym

    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
    (
    1.56
    सी
    1.39
    ای
    1.34
    ların
    1.29
    מן
    1.20
    cadherin
    1.20
    impanan
    1.17
    اریخ
    1.16
    более
    1.16
    gambar
    1.16
    POSITIVE LOGITS
    et
    1.35
    an
    1.30
    .
    1.27
    كَ
    1.17
    os
    1.15
    ır
    1.12
    ור
    1.12
    ى
    1.12
    ina
    1.06
    eren
    1.03
    Activations Density 0.000%

    No Known Activations