© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159291
    Prev
    Next
    INDEX
    Explanations

    ira

    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
    ur
    1.36
    o
    1.35
    er
    1.30
    h
    1.24
    ar
    1.23
    ol
    1.19
    el
    1.18
    il
    1.15
    im
    1.15
    og
    1.14
    POSITIVE LOGITS
    ت
    1.19
    П
    1.18
    dır
    1.16
    Ꮡ
    1.11
    Произ
    1.05
    ној
    1.05
    。
    1.04
    ।
    1.03
    ка
    1.00
    ッド
    0.98
    Activations Density 0.000%

    No Known Activations