© 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. 51978
    Prev
    Next
    INDEX
    Explanations

    ranking or position

    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
    ミニ
    0.38
    锑
    0.37
     الظ
    0.36
    ွင်း
    0.35
     Mini
    0.33
    𝓾
    0.33
    綁
    0.33
    mini
    0.33
    <0xB5>
    0.33
     мини
    0.32
    POSITIVE LOGITS
     position
    0.48
     placement
    0.48
     posicion
    0.46
     Position
    0.46
     위치
    0.45
     positioning
    0.45
     somewhere
    0.44
     placements
    0.43
    的位置
    0.43
    位置
    0.42
    Activations Density 0.138%

    No Known Activations