© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 988
    Prev
    Next
    INDEX
    Explanations

    periods, especially at the end of a sentence or phrase, and decimals

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     itſelf
    -0.53
    
    -0.53
    <bos>
    -0.52
     виправивши
    -0.52
     well
    -0.50
     decompression
    -0.49
     disambiguazione
    -0.49
     proper
    -0.48
     tax
    -0.47
     persistence
    -0.47
    POSITIVE LOGITS
    rawDesc
    0.76
    SourceChecksum
    0.73
    mergeFrom
    0.68
    MockMvc
    0.65
    GOTREF
    0.65
    ibatis
    0.61
    XmlAccessorType
    0.60
    netbeans
    0.60
    posables
    0.60
    DockStyle
    0.59
    Activations Density 3.324%

    No Known Activations