© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116285
    Prev
    Next
    INDEX
    Explanations

    truly happy

    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_27_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
    project
    0.27
     optimal
    0.27
    graphic
    0.26
    restore
    0.26
    myForm
    0.26
    const
    0.26
     s
    0.26
    ])))
    0.25
     ಕಾ
    0.25
    feature
    0.24
    POSITIVE LOGITS
     بالنسبة
    0.27
    तोष
    0.27
    很简单
    0.27
     بالنسبه
    0.26
    じゃない
    0.25
     বয়সী
    0.25
    藓
    0.25
     divul
    0.25
    溟
    0.25
     designee
    0.25
    Activations Density 0.001%

    No Known Activations