© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10349
    Prev
    Next
    INDEX
    Explanations

    C++ code fragments

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    parsedMessage
    -0.82
     mergeFrom
    -0.79
    ReusableCell
    -0.76
     صوتيه
    -0.73
    ENODEV
    -0.73
    WarningLevel
    -0.70
    DebuggerNonUser
    -0.69
    Искәрмәләр
    -0.69
     GenerationType
    -0.69
     propOrder
    -0.66
    POSITIVE LOGITS
     MCI
    0.50
    Portale
    0.49
    chloric
    0.44
     față
    0.43
    ẾT
    0.42
     spē
    0.41
     adresa
    0.41
    quelize
    0.40
    lorette
    0.40
     Ayr
    0.39
    Activations Density 1.652%

    No Known Activations