© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167543
    Prev
    Next
    INDEX
    Explanations

    greetings and interjections

    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_31_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
     please
    0.58
    !,
    0.58
     !,
    0.57
     Please
    0.56
    !:
    0.54
    ！
    0.52
     !
    0.52
    !”,
    0.52
    !
    0.51
    !”
    0.51
    POSITIVE LOGITS
     கேரள
    0.42
     tenants
    0.39
     oversaw
    0.38
    Ⓒ
    0.38
    მას
    0.36
    inct
    0.36
    ᵗ
    0.36
    ➛
    0.35
     серед
    0.35
    ceiver
    0.34
    Activations Density 0.013%

    No Known Activations