© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260928
    Prev
    Next
    INDEX
    Explanations

    gitlab CI, pipelines, issue

    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_5_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
    1.65
    ai
    1.49
    j
    1.49
    o
    1.48
    ne
    1.39
    g
    1.28
    na
    1.27
    la
    1.25
    ni
    1.24
    ri
    1.23
    POSITIVE LOGITS
    تون
    1.20
    تك
    1.16
    اني
    1.14
    تي
    1.12
    انية
    1.05
    ية
    1.04
    انو
    1.04
    تين
    1.04
    تها
    1.03
    ный
    1.01
    Activations Density 0.000%

    No Known Activations