© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176176
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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_24_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
    зуа
    0.42
    沨
    0.41
     bądź
    0.40
     Зараз
    0.40
    ান্ট
    0.40
    აწილ
    0.40
     עם
    0.40
     Тер
    0.39
     компонентов
    0.39
    旃
    0.39
    POSITIVE LOGITS
     gent
    0.44
    ု
    0.43
     uf
    0.40
     softly
    0.38
    ,$$
    0.35
    upati
    0.35
    utada
    0.35
     softener
    0.34
     gentle
    0.34
     tempting
    0.33
    Activations Density 0.001%

    No Known Activations