© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 130491
    Prev
    Next
    INDEX
    Explanations

    -

    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_25_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
     アメリカ
    0.41
     Geschmack
    0.38
    ൦
    0.37
     അമേരിക്ക
    0.36
     نبدا
    0.36
     Bewohner
    0.36
     জানায়
    0.35
     wohn
    0.35
     Feuer
    0.34
    ppler
    0.34
    POSITIVE LOGITS
    促
    0.37
    沏
    0.36
     Guns
    0.36
    잃
    0.36
     cutoff
    0.35
    ्रिय
    0.35
     congest
    0.34
    िकी
    0.34
    ัฒ
    0.34
    ंबल
    0.34
    Activations Density 0.002%

    No Known Activations