© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198569
    Prev
    Next
    INDEX
    Explanations

    shrilling alarm, boat captain, shrink

    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_4_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
    ل
    1.51
    ל
    1.38
    ت
    1.29
    at
    1.24
    т
    1.20
     rozpoczę
    1.19
    لە
    1.13
    льзя
    1.07
    or
    1.05
    et
    1.03
    POSITIVE LOGITS
    s
    1.39
    는
    1.21
    was
    1.18
    是
    1.17
    t
    1.05
    的
    1.02
    를
    1.02
    的操作
    1.02
     was
    1.01
    ↵
    0.98
    Activations Density 0.001%

    No Known Activations