© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39648
    Prev
    Next
    INDEX
    Explanations

    deduplication

    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_57_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
    িয়াল
    0.41
    вало
    0.39
    izzate
    0.39
    izy
    0.38
    iral
    0.38
    الا
    0.37
    лизация
    0.37
    럴
    0.37
     impeachment
    0.37
     Bally
    0.37
    POSITIVE LOGITS
    pi
    0.47
    ̣c
    0.46
     pi
    0.46
    oci
    0.42
    trasound
    0.42
    pping
    0.41
    opol
    0.41
    プション
    0.41
    ustom
    0.40
    ṣ
    0.40
    Activations Density 0.000%

    No Known Activations