© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213781
    Prev
    Next
    INDEX
    Explanations

    object

    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_47_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
    NIC
    0.37
    Ready
    0.36
     exclusions
    0.36
     реали
    0.36
    figure
    0.35
    Bird
    0.34
    Pretty
    0.33
    傍
    0.33
    Tal
    0.33
    ref
    0.33
    POSITIVE LOGITS
     Кара
    0.37
     кар
    0.37
    ဖြစ်သည်။
    0.37
     juveniles
    0.37
     Enum
    0.37
     नाइन
    0.37
     Tween
    0.37
     పంచ
    0.36
    කර
    0.36
     Tanganyika
    0.36
    Activations Density 0.004%

    No Known Activations