© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38097
    Prev
    Next
    INDEX
    Explanations

    stating an assumption

    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_11_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
    ers
    0.63
    restrict
    0.59
    腭
    0.59
     πρώτη
    0.59
     necessárias
    0.58
     necessários
    0.58
     prezident
    0.57
     Betrieb
    0.57
    version
    0.56
    referred
    0.56
    POSITIVE LOGITS
    на
    0.71
    ята
    0.65
    мо
    0.64
    я
    0.63
    ன்
    0.60
    ї
    0.59
    ли
    0.58
    ям
    0.55
     legumes
    0.55
     более
    0.54
    Activations Density 0.006%

    No Known Activations