© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39765
    Prev
    Next
    INDEX
    Explanations

    say "suffix" words

    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_57_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
     é
    0.51
     Um
    0.47
     um
    0.46
    Um
    0.39
     Os
    0.39
    Os
    0.38
     os
    0.37
    নেস
    0.37
     É
    0.37
     ADA
    0.36
    POSITIVE LOGITS
    çe
    0.48
     Sto
    0.47
    Sto
    0.46
    âne
    0.41
    Sul
    0.40
     sul
    0.39
    Blo
    0.39
    Employment
    0.38
    ãn
    0.38
    âl
    0.38
    Activations Density 0.000%

    No Known Activations