© 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-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4292
    Prev
    Next
    INDEX
    Explanations

    snippets of Java or C++ array or list code, or psuedocode

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chaus
    -0.50
    ettbewer
    -0.48
     مرئيه
    -0.46
     ListNode
    -0.45
     aéri
    -0.44
    hlí
    -0.44
    Ray
    -0.44
    cassert
    -0.43
    àm
    -0.43
    protobuf
    -0.43
    POSITIVE LOGITS
    numerusform
    0.67
    ⓧ
    0.66
    ]--;
    0.60
    elemField
    0.57
     lenker
    0.55
    amoan
    0.52
     jLabel
    0.52
     intptr
    0.50
     TestBed
    0.50
     resultCode
    0.49
    Activations Density 1.833%

    No Known Activations