© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3659
    Prev
    Next
    INDEX
    Explanations

    colons and the words 'set', 'newValue', 'bool', 'double', 'trim', 'annually', 'assignment', and 'function' in code

    oai_token-act-pair · gemini-2.0-flash

    Code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    تقاوى
    -0.75
     surla
    -0.68
    Gizmos
    -0.57
    oneofs
    -0.55
    ztat
    -0.54
    Jereo
    -0.52
     lèvres
    -0.52
    +:+
    -0.51
    AntiForgeryToken
    -0.51
    Населення
    -0.50
    POSITIVE LOGITS
    ↵
    0.52
    MutableLiveData
    0.50
    ')")
    0.50
    helial
    0.50
     kaynağından
    0.49
     invokingState
    0.49
     StringTokenizer
    0.46
    istungen
    0.46
    NavController
    0.45
    sement
    0.45
    Activations Density 1.057%

    No Known Activations