© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216772
    Prev
    Next
    INDEX
    Explanations

    incentives for investment or benefits

    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
    بيع
    0.40
     hearth
    0.32
     produse
    0.31
     cos
    0.31
     enfrenta
    0.31
    KILL
    0.31
    ฆ
    0.31
    hear
    0.30
     सच
    0.30
    Cos
    0.30
    POSITIVE LOGITS
     Track
    0.37
     Venezuela
    0.37
     minorities
    0.37
    縷
    0.37
    lining
    0.35
     railways
    0.34
    avelength
    0.33
    anyl
    0.33
     সংখ্যাল
    0.33
     Wednesday
    0.32
    Activations Density 0.001%

    No Known Activations