© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45544
    Prev
    Next
    INDEX
    Explanations

    quantum entanglement or cryptography

    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_3_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
    ية
    0.87
    (
    0.83
     jogador
    0.71
     for
    0.65
     jeweler
    0.65
     dehors
    0.64
     be
    0.61
     وأ
    0.61
    }></
    0.59
    国
    0.59
    POSITIVE LOGITS
    slip
    0.60
    usr
    0.59
    tx
    0.58
    power
    0.58
    storey
    0.58
    äksi
    0.57
    слан
    0.56
    table
    0.56
    vpn
    0.56
    plastics
    0.54
    Activations Density 0.009%

    No Known Activations