© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79183
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    डीएम
    0.38
     आलोक
    0.37
    branches
    0.37
    알
    0.36
    বর্ধ
    0.35
    ocentric
    0.35
     பணி
    0.34
     मर्यादा
    0.34
    বাগ
    0.34
    𝙰
    0.34
    POSITIVE LOGITS
    лта
    0.37
    перы
    0.37
    ították
    0.37
    теп
    0.36
    াদিত
    0.35
    ître
    0.35
    тинг
    0.35
     těž
    0.35
    шна
    0.35
     ఆగ
    0.34
    Activations Density 0.001%

    No Known Activations