© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22845
    Prev
    Next
    INDEX
    Explanations

    held

    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_56_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
    unpriv
    0.37
    चय
    0.36
    blocking
    0.36
     runner
    0.35
    leted
    0.35
    anaconda
    0.34
    찼
    0.33
    encoded
    0.33
    runner
    0.32
    ᱜ
    0.32
    POSITIVE LOGITS
     held
    3.58
    held
    3.17
    Held
    3.14
     Held
    3.08
     برگزار
    1.84
     održ
    1.45
     diadakan
    1.41
    举行
    1.38
    持
    1.38
     অনুষ্ঠিত
    1.33
    Activations Density 0.037%

    No Known Activations