© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93158
    Prev
    Next
    INDEX
    Explanations

    theMethod number used: 1Reason for explanation: All MAX_ACTIVATING_TOKENS are "the"

    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
     motifs
    0.43
    <em>
    0.43
     offences
    0.43
    constraints
    0.41
     modalities
    0.40
    transactions
    0.40
     critères
    0.39
     a
    0.39
     اقدامات
    0.39
     constraints
    0.39
    POSITIVE LOGITS
    secret
    0.71
     make
    0.71
    single
    0.69
    make
    0.66
     secret
    0.63
     SECRET
    0.63
     l
    0.63
     SINGLE
    0.62
     MAKE
    0.60
     single
    0.57
    Activations Density 0.026%

    No Known Activations