© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52406
    Prev
    Next
    INDEX
    Explanations

    Args: documentation context

    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_31_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
    athl
    0.29
     sejak
    0.27
    िद
    0.27
    浗
    0.27
     tyres
    0.26
     tetra
    0.26
    仆
    0.26
     uga
    0.25
     Offset
    0.24
     मुआवजे
    0.24
    POSITIVE LOGITS
    排行榜
    0.33
     ফলাফল
    0.33
    STS
    0.32
     STS
    0.30
     பார்வைய
    0.29
     garnished
    0.29
     formulated
    0.29
     importing
    0.29
    ository
    0.28
    璋
    0.28
    Activations Density 0.029%

    No Known Activations