© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36462
    Prev
    Next
    INDEX
    Explanations

    petting zoo

    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_3_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
    O
    0.92
    J
    0.85
    OF
    0.80
    S
    0.79
    ை
    0.79
    ı
    0.74
    F
    0.74
    ं
    0.74
     a
    0.73
    E
    0.73
    POSITIVE LOGITS
     impor
    0.70
    iiv
    0.66
    دي
    0.64
     échanc
    0.64
     showered
    0.64
     аппара
    0.64
     οπο
    0.63
     Нико
    0.63
     Евро
    0.63
    য়া
    0.62
    Activations Density 0.003%

    No Known Activations