© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27230
    Prev
    Next
    INDEX
    Explanations

    clutter or fraud

    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_10_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
     लेकिन
    0.49
     margine
    0.48
     negation
    0.46
     legger
    0.46
    েক
    0.44
     behöver
    0.44
     跳
    0.44
     مت
    0.44
     للم
    0.44
     schwer
    0.44
    POSITIVE LOGITS
    t
    0.70
    d
    0.58
     Astro
    0.52
    ט
    0.51
    aval
    0.47
    /=
    0.46
    Repository
    0.44
    ס
    0.44
    ｔ
    0.43
    q
    0.42
    Activations Density 0.000%

    No Known Activations