© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 29911
    Prev
    Next
    INDEX
    Explanations

    days, fruits, numbers, Marco Polo

    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_40_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
     Steam
    0.40
    accuracy
    0.38
    厚生
    0.37
     каз
    0.37
     حمله
    0.36
     mos
    0.36
    诵
    0.36
    脤
    0.35
     Mos
    0.35
     veine
    0.35
    POSITIVE LOGITS
    Sir
    0.40
     Gaia
    0.40
     Христо
    0.38
    设
    0.37
     spin
    0.37
    Gaia
    0.36
     αρ
    0.36
    iconductor
    0.36
    stin
    0.36
    xF
    0.34
    Activations Density 0.004%

    No Known Activations