© 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. 8615
    Prev
    Next
    INDEX
    Explanations

    Java code-related API calls, parameters, and variables, particularly those involving text manipulation or data retrieval

    oai_token-act-pair · gemini-2.0-flash

    String manipulation

    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
     itſelf
    -0.83
     Monfieur
    -0.80
     Majefty
    -0.77
     pleaſure
    -0.76
     Houſe
    -0.73
     houſe
    -0.72
     purpoſe
    -0.72
     themſelves
    -0.71
     himſelf
    -0.71
    ſelf
    -0.70
    POSITIVE LOGITS
     string
    0.58
    TextUtils
    0.55
    DateString
    0.55
     
    0.54
     te
    0.54
     Te
    0.52
    VarChar
    0.52
     strlen
    0.50
    StringLength
    0.50
     Vikipedi
    0.50
    Activations Density 1.848%

    No Known Activations