© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4360
    Prev
    Next
    INDEX
    Explanations

    very modified adjectives

    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_38_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
    pdfs
    0.41
    杞
    0.40
     undefined
    0.39
     Udd
    0.38
     Noh
    0.38
     Batch
    0.38
     inver
    0.37
     ->
    0.37
     بالك
    0.37
     Vetter
    0.37
    POSITIVE LOGITS
     extremes
    0.50
     extremadamente
    0.50
     emphasise
    0.49
     horrible
    0.47
    extreme
    0.47
     awful
    0.46
     extreme
    0.45
     horrendous
    0.44
     dreadful
    0.44
    extremely
    0.44
    Activations Density 0.012%

    No Known Activations