© 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. 23112
    Prev
    Next
    INDEX
    Explanations

    jaw

    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
     f
    2.59
     ف
    1.88
     फ
    1.48
    f
    1.41
    ฟ
    1.32
     ফ
    1.25
     ฟ
    1.25
    ｆ
    1.20
     ф
    1.17
    <0x86>
    1.14
    POSITIVE LOGITS
     डीएल
    0.40
    Jaw
    0.37
     stake
    0.36
    jaw
    0.35
    짱
    0.34
    ropy
    0.34
    css
    0.34
     jaw
    0.33
    جب
    0.33
    osphate
    0.33
    Activations Density 0.003%

    No Known Activations