© 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. 258713
    Prev
    Next
    INDEX
    Explanations

    prime number

    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
    гистра
    0.38
    իմ
    0.36
    шим
    0.35
    filtration
    0.35
    τω
    0.33
     হা
    0.33
    👷
    0.33
    ърква
    0.33
    رک
    0.33
    Avro
    0.33
    POSITIVE LOGITS
     c
    0.42
     l
    0.41
     Kevin
    0.38
     Susp
    0.38
     imagin
    0.38
     Song
    0.37
     Eric
    0.37
     g
    0.36
     Reels
    0.36
     Praise
    0.36
    Activations Density 0.012%

    No Known Activations