© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152761
    Prev
    Next
    INDEX
    Explanations

    common words and structure

    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_60_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
    il
    0.58
     Z
    0.57
    Z
    0.55
     الز
    0.53
    “
    0.51
    “-
    0.50
    "-
    0.48
    O
    0.48
    ihe
    0.47
    ”
    0.47
    POSITIVE LOGITS
     that
    0.57
     And
    0.56
    And
    0.55
     so
    0.52
     your
    0.51
     phot
    0.50
     these
    0.49
     its
    0.49
     they
    0.49
     our
    0.48
    Activations Density 0.000%

    No Known Activations