© 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. 163763
    Prev
    Next
    INDEX
    Explanations

    coastal and water place names

    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
     consigli
    0.52
     melaksanakan
    0.51
    <start_of_image>
    0.51
    Alfred
    0.50
    aduras
    0.49
    Francesco
    0.49
     представи
    0.49
    ட்சி
    0.48
    ography
    0.48
    क्ट
    0.48
    POSITIVE LOGITS
    owntown
    0.55
    殮
    0.55
    ون
    0.53
     冖
    0.53
     入っ
    0.53
    ol
    0.52
     haloes
    0.52
    ov
    0.52
    ୦
    0.52
    yecto
    0.52
    Activations Density 0.000%

    No Known Activations