© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36239
    Prev
    Next
    INDEX
    Explanations

    numbers with decimal points

    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_31_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
     ständig
    0.38
     hráč
    0.38
     radar
    0.37
    鸟
    0.37
     직선
    0.36
    ುದ
    0.36
     scrut
    0.35
    髙
    0.35
    Sensor
    0.35
     evade
    0.35
    POSITIVE LOGITS
     Com
    0.45
     ክፍል
    0.40
     ఒ
    0.40
    ILLS
    0.39
     Ibn
    0.39
     Peaceful
    0.39
    勧め
    0.38
    idges
    0.38
     दोष
    0.37
    和平
    0.37
    Activations Density 0.006%

    No Known Activations