© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65120
    Prev
    Next
    INDEX
    Explanations

    predator/predicate

    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_46_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
     তালা
    0.39
    发明
    0.39
    Cyan
    0.39
    قع
    0.37
    통산
    0.37
    रेज
    0.36
    gin
    0.36
    ɚ
    0.35
    々の
    0.35
    igkeits
    0.35
    POSITIVE LOGITS
    Pred
    3.58
     Pred
    3.55
    pred
    3.39
     pred
    3.22
     predator
    3.13
     predators
    3.05
     Predator
    2.98
     Predators
    2.92
     predicate
    2.83
     predation
    2.80
    Activations Density 0.156%

    No Known Activations