© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90087
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    </strong>
    0.33
     Undoubtedly
    0.33
    ORICAL
    0.32
    ATED
    0.32
    IÓN
    0.32
    ONTAL
    0.31
    ¿
    0.31
    骼
    0.31
    髓
    0.31
    
    0.31
    POSITIVE LOGITS
     ID
    0.56
     API
    0.56
     VBA
    0.55
     CRUD
    0.55
     node
    0.54
     mode
    0.54
     JWT
    0.54
     CRL
    0.54
     PATH
    0.53
     NODE
    0.53
    Activations Density 0.011%

    No Known Activations