© 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. 145705
    Prev
    Next
    INDEX
    Explanations

    Am followed by specific endings

    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
    a
    1.66
    اً
    1.34
    aim
    1.24
    این
    1.24
    app
    1.20
    ب
    1.17
    of
    1.16
    aren
    1.14
    arean
    1.13
    ussa
    1.12
    POSITIVE LOGITS
    ри
    1.74
    يس
    1.51
    طي
    1.45
    يز
    1.43
    리
    1.43
    يش
    1.37
    أي
    1.36
    شي
    1.35
    ات
    1.30
    رك
    1.25
    Activations Density 0.001%

    No Known Activations