© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257663
    Prev
    Next
    INDEX
    Explanations

    estimating quantity or possibility

    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_22_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
    bollah
    0.48
    ેલા
    0.46
    oubtedly
    0.44
     Antibodies
    0.43
    ources
    0.42
    的任务
    0.41
    ː
    0.40
    ugoslav
    0.40
    rifugal
    0.40
    antibodies
    0.39
    POSITIVE LOGITS
    ଵ
    0.46
     बाज
    0.44
     processor
    0.43
     inher
    0.41
    📟
    0.40
    বুঝ
    0.40
     なっ
    0.40
     unending
    0.39
     mindset
    0.39
    편집
    0.39
    Activations Density 0.001%

    No Known Activations