© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14118
    Prev
    Next
    INDEX
    Explanations

    listing items after a number

    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_13_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
    测
    0.51
    hen
    0.46
    ash
    0.44
    youth
    0.44
     neutrality
    0.43
    uí
    0.43
    嚴重
    0.42
    严重
    0.42
     sufficient
    0.41
    strength
    0.41
    POSITIVE LOGITS
     раза
    0.57
     iran
    0.57
    ڈ
    0.56
    вало
    0.55
    т
    0.55
    אר
    0.54
     мото
    0.54
     Chakraborty
    0.54
     içinde
    0.53
     самом
    0.52
    Activations Density 0.013%

    No Known Activations