© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201255
    Prev
    Next
    INDEX
    Explanations

    anticipatory

    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_12_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
     С
    0.36
    คน
    0.35
     godine
    0.35
     人
    0.34
     पचास
    0.34
    ]:
    0.33
     године
    0.33
     cinq
    0.33
     близько
    0.33
     человек
    0.32
    POSITIVE LOGITS
    ajuan
    0.37
    έ
    0.33
    ruits
    0.32
     satisfactor
    0.32
    icama
    0.32
     Imp
    0.32
    FreeBuf
    0.32
    ită
    0.31
    ități
    0.31
    痧
    0.31
    Activations Density 0.000%

    No Known Activations