© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13464
    Prev
    Next
    INDEX
    Explanations

    core premise

    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
     al
    0.52
     idol
    0.50
     ia
    0.48
     Idol
    0.47
    🎄
    0.47
    мат
    0.46
     apari
    0.46
     indywidual
    0.46
     чемпиона
    0.46
     aquare
    0.46
    POSITIVE LOGITS
    راه
    0.47
    航
    0.44
    在新
    0.41
    ست
    0.40
    زا
    0.40
    ecimiento
    0.40
    ثة
    0.40
    بعة
    0.40
    ົດ
    0.40
    ექს
    0.39
    Activations Density 0.001%

    No Known Activations