© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6718
    Prev
    Next
    INDEX
    Explanations

    code syntax, especially related to error handling and loops, as well as potentially the start and end of code blocks.

    oai_token-act-pair · gemini-2.0-flash

    number six

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    4
    -0.96
    5
    -0.95
    7
    -0.94
    enumi
    -0.88
    ThroughAttribute
    -0.81
    3
    -0.80
    8
    -0.79
     CreateTagHelper
    -0.72
     createContext
    -0.71
    NgModule
    -0.68
    POSITIVE LOGITS
     sechs
    0.86
     sixth
    0.85
     six
    0.85
     Sixth
    0.84
     Six
    0.76
     шесть
    0.75
     seis
    0.75
    0.72
     SIX
    0.69
    Six
    0.68
    Activations Density 2.333%

    No Known Activations