© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200795
    Prev
    Next
    INDEX
    Explanations

    equation

    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_12_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
    }\,
    0.45
     těchto
    0.44
    රු
    0.42
     avec
    0.42
    عية
    0.41
     определён
    0.41
     kanssa
    0.41
    ש
    0.41
    罗
    0.41
    กับ
    0.41
    POSITIVE LOGITS
    ⬥
    0.46
    GALAD
    0.45
     ciphertext
    0.43
     समितियों
    0.40
     निबंध
    0.40
     petition
    0.40
    லாத
    0.40
    dining
    0.40
     tional
    0.39
     Divid
    0.39
    Activations Density 0.000%

    No Known Activations