© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208608
    Prev
    Next
    INDEX
    Explanations

    well (various languages)

    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_56_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
     Mental
    0.59
    Mental
    0.59
     mental
    0.56
     만
    0.46
    mental
    0.45
     mentale
    0.43
     মানসিক
    0.42
    един
    0.40
     मानसिक
    0.40
    厓
    0.40
    POSITIVE LOGITS
     well
    0.56
     잘
    0.55
    well
    0.54
     хорошо
    0.49
    良く
    0.48
     добре
    0.46
    よく
    0.45
     Well
    0.45
    following
    0.44
    embeddings
    0.43
    Activations Density 0.018%

    No Known Activations