© 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. 80189
    Prev
    Next
    INDEX
    Explanations

    configurable parameters

    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
     I
    1.66
    ك
    1.50
    te
    1.42
    1
    1.37
    个
    1.31
    ul
    1.30
    ia
    1.30
    um
    1.24
    ना
    1.20
    na
    1.18
    POSITIVE LOGITS
    ב
    1.30
     کل
    1.29
     powied
    1.27
     که
    1.25
    но
    1.23
     το
    1.23
     мы
    1.15
    اک
    1.14
    )’
    1.14
     لی
    1.13
    Activations Density 0.000%

    No Known Activations