© 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. 38119
    Prev
    Next
    INDEX
    Explanations

    fooled or fooling

    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
    दस
    0.74
    9
    0.64
    1
    0.61
    و
    0.59
    ką
    0.59
    fif
    0.57
    ርዝ
    0.57
    다
    0.55
    examine
    0.55
    for
    0.54
    POSITIVE LOGITS
    дентифика
    0.53
    는
    0.49
    ↵
    0.48
    ophile
    0.47
    ائه
    0.47
     sobreviv
    0.47
    ждане
    0.47
     refugi
    0.47
     الذ
    0.47
     is
    0.46
    Activations Density 0.040%

    No Known Activations