© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141871
    Prev
    Next
    INDEX
    Explanations

    expense categories

    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_46_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
    Pay
    0.45
     един
    0.42
     Mers
    0.41
     मानी
    0.41
     Един
    0.41
    EA
    0.39
     Epson
    0.38
    屠
    0.38
     اخت
    0.38
     इस्ला
    0.37
    POSITIVE LOGITS
     Salv
    0.40
     salv
    0.37
    snackbar
    0.36
    bnb
    0.36
    ymethyl
    0.36
    stwa
    0.35
     BNP
    0.35
     delinquency
    0.35
     Compiled
    0.34
    sal
    0.34
    Activations Density 0.009%

    No Known Activations