© 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. 13046
    Prev
    Next
    INDEX
    Explanations

    0.001

    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
    ли
    0.44
    т
    0.42
    ﻭ
    0.41
     proximité
    0.39
    ⓝ
    0.39
    не
    0.39
    を読む
    0.38
    建て
    0.38
     brunâtre
    0.38
    ANY
    0.38
    POSITIVE LOGITS
     Hua
    0.40
    steigen
    0.39
     Form
    0.39
    ↵
    0.38
     Pina
    0.37
     Flu
    0.36
    ptt
    0.36
     Conta
    0.36
    ],”
    0.36
     Pena
    0.36
    Activations Density 0.004%

    No Known Activations