© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34060
    Prev
    Next
    INDEX
    Explanations

    comparing or relating different things

    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
     governo
    0.31
    et
    0.30
    ى
    0.30
     nowe
    0.28
     tradiz
    0.26
     potere
    0.25
    ет
    0.25
    ید
    0.25
    জ
    0.25
     griego
    0.25
    POSITIVE LOGITS
    src
    0.29
    arı
    0.27
    '
    0.25
    １
    0.23
    1
    0.21
    状況
    0.21
    kor
    0.21
    、
    0.21
    ög
    0.20
    old
    0.20
    Activations Density 0.011%

    No Known Activations