© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 207121
    Prev
    Next
    INDEX
    Explanations

    weakening or damaging progress, trust, or sales

    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_25_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
    ake
    0.24
     rendez
    0.22
     pooling
    0.22
    됨
    0.21
     उर्फ
    0.21
    भी
    0.21
     docking
    0.21
    otr
    0.21
     tắm
    0.21
     update
    0.20
    POSITIVE LOGITS
    ricamente
    0.24
     Reasons
    0.22
     Advantages
    0.22
    太阳
    0.20
     Faktor
    0.20
    瑗
    0.20
     Kø
    0.19
     Phrases
    0.19
     Roses
    0.19
     Scalars
    0.19
    Activations Density 0.013%

    No Known Activations