© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58047
    Prev
    Next
    INDEX
    Explanations

    and

    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_59_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
     have
    0.95
    Have
    0.90
     Have
    0.85
    have
    0.76
    ’
    0.69
     HAVE
    0.68
     am
    0.60
     Were
    0.60
    Were
    0.59
     hebben
    0.57
    POSITIVE LOGITS
    doesn
    0.55
    has
    0.46
     Doesn
    0.46
     doesn
    0.40
    قيقي
    0.40
    does
    0.39
    gives
    0.39
     knows
    0.38
     '':
    0.38
     DOES
    0.37
    Activations Density 0.007%

    No Known Activations