© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260435
    Prev
    Next
    INDEX
    Explanations

    photosynthesis

    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_22_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
    గానే
    0.39
     nhớ
    0.39
    getInfo
    0.39
     मंगलवार
    0.38
    温柔
    0.38
     Tuesday
    0.38
    记住
    0.38
    曳
    0.37
     особое
    0.37
     अच्छे
    0.37
    POSITIVE LOGITS
    eneg
    0.47
    ائن
    0.45
    ્યૂ
    0.45
     felicidad
    0.44
    unks
    0.43
     proviso
    0.43
    štění
    0.43
     قار
    0.43
    度の
    0.43
     incont
    0.42
    Activations Density 0.000%

    No Known Activations