© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31828
    Prev
    Next
    INDEX
    Explanations

    say "in" or "en"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Charlotte
    0.41
    μβ
    0.39
    obucket
    0.39
     বাহাদুর
    0.39
     संत
    0.38
     nhánh
    0.38
    сү
    0.38
    ℓ
    0.38
    Michael
    0.38
     assemble
    0.38
    POSITIVE LOGITS
     Mojo
    0.48
     Moe
    0.47
     Moff
    0.41
    Ingredient
    0.40
     Moffat
    0.39
     MO
    0.38
    eos
    0.38
     UNF
    0.38
     Съ
    0.37
     Un
    0.37
    Activations Density 0.009%

    No Known Activations