© 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. 248755
    Prev
    Next
    INDEX
    Explanations

    vertigo

    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
     d
    2.34
     د
    1.73
     д
    1.71
     द
    1.46
    <0x93>
    1.41
     দ
    1.34
     ד
    1.22
    d
    1.12
    ด
    1.12
    ｄ
    1.12
    POSITIVE LOGITS
    Gn
    0.35
     downgraded
    0.35
    sna
    0.35
    dow
    0.35
    ूत
    0.34
    وران
    0.34
    深化
    0.34
    ondere
    0.34
    DropDownStyle
    0.34
    ত্ত
    0.33
    Activations Density 0.003%

    No Known Activations