© 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. 212565
    Prev
    Next
    INDEX
    Explanations

    occurrence

    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
    ’
    1.16
    ти
    1.13
    ことなく
    1.12
    ле
    1.09
    inin
    1.05
    ↵↵
    0.99
    ד
    0.96
     множе
    0.93
    x
    0.92
    siniz
    0.92
    POSITIVE LOGITS
    า
    1.44
    م
    1.32
    UN
    1.31
    ма
    1.30
    و
    1.22
     a
    1.16
    "
    1.16
    ing
    1.12
     of
    1.12
    AL
    1.09
    Activations Density 0.000%

    No Known Activations