© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249848
    Prev
    Next
    INDEX
    Explanations

    global language

    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
    팟
    0.36
    Atlantic
    0.35
    ശാല
    0.35
     राइट
    0.34
     "\""
    0.34
    ुत
    0.34
    ☆
    0.34
    rapid
    0.33
    快速
    0.33
    indirect
    0.33
    POSITIVE LOGITS
    가의
    0.70
    가
    0.68
    제
    0.64
    가를
    0.62
    가가
    0.61
    加
    0.53
    제로
    0.52
    제의
    0.46
    esta
    0.44
     Ga
    0.44
    Activations Density 0.001%

    No Known Activations