© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62295
    Prev
    Next
    INDEX
    Explanations

    results in

    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
    ка
    0.86
    crisis
    0.79
     Информация
    0.70
    🗓
    0.67
    أ
    0.66
    და
    0.65
    ма
    0.64
    仵
    0.64
    glow
    0.63
    多样
    0.63
    POSITIVE LOGITS
     l
    0.79
     can
    0.69
     )
    0.67
     du
    0.66
     (
    0.65
    ");
    0.57
     OUT
    0.57
    )：
    0.56
     il
    0.55
     sailors
    0.55
    Activations Density 0.026%

    No Known Activations