© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48583
    Prev
    Next
    INDEX
    Explanations

    making followed by a noun

    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_10_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
     to
    0.34
     llamadas
    0.34
    ール
    0.33
     involution
    0.33
     Barça
    0.32
     игроков
    0.32
    תו
    0.31
    </h3>
    0.31
     unités
    0.31
    itettura
    0.31
    POSITIVE LOGITS
    IR
    0.39
    ah
    0.35
    i
    0.34
    Siehe
    0.33
    ност
    0.33
     sorgen
    0.33
    ahh
    0.32
    SI
    0.32
    UT
    0.32
    OK
    0.31
    Activations Density 0.006%

    No Known Activations