© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12423
    Prev
    Next
    INDEX
    Explanations

    passenger seat

    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_13_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
     Vào
    0.52
    ي
    0.49
     Método
    0.48
    ప్తి
    0.48
     envío
    0.47
     Rousse
    0.47
    ی
    0.47
     Valores
    0.47
    𝐸
    0.47
     ポリ
    0.46
    POSITIVE LOGITS
    because
    0.51
     because
    0.45
    last
    0.44
    story
    0.44
     getting
    0.44
    gom
    0.43
    ǧ
    0.43
    less
    0.43
    liner
    0.43
     building
    0.43
    Activations Density 0.002%

    No Known Activations