© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83207
    Prev
    Next
    INDEX
    Explanations

    bal- words

    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_0_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
    ের
    2.05
    是
    1.57
    ਾ
    1.41
    中
    1.41
    和
    1.40
    ти
    1.38
    >
    1.38
    কে
    1.34
     and
    1.34
    ায়
    1.31
    POSITIVE LOGITS
    м
    1.78
    la
    1.75
    lar
    1.51
    berly
    1.47
    ت
    1.47
    م
    1.45
    ya
    1.44
    dan
    1.43
    ل
    1.41
    л
    1.38
    Activations Density 0.000%

    No Known Activations