© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31138
    Prev
    Next
    INDEX
    Explanations

    years or numbers

    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_7_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
    of
    0.58
    ة
    0.57
    𝖐
    0.50
    و
    0.49
     naše
    0.46
    আমাদের
    0.46
    o
    0.46
     unsere
    0.45
     vår
    0.44
    在
    0.44
    POSITIVE LOGITS
     to
    0.61
    ר
    0.52
    ץ
    0.46
    to
    0.46
    רות
    0.40
    רק
    0.40
    ョン
    0.38
    رین
    0.38
    р
    0.38
    ות
    0.37
    Activations Density 0.000%

    No Known Activations