© 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. 8066
    Prev
    Next
    INDEX
    Explanations

    text arguing for the importance of passionately teaching the Christian faith to students and encouraging them to put their faith into practice.

    oai_token-act-pair · 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
    SourceChecksum
    -0.72
    PositiveButton
    -0.66
    Rujuakan
    -0.62
    はじめに
    -0.61
    <?
    -0.59
    зулта
    -0.58
     XNUMX
    -0.58
    __["
    -0.57
    ఔ
    -0.56
    ondissement
    -0.56
    POSITIVE LOGITS
     hood
    0.48
    UnknownFieldSet
    0.48
    brigens
    0.48
    الإنجليزية
    0.46
    RefNanny
    0.45
     deposition
    0.44
    mappedBy
    0.43
    WithMany
    0.43
    ardos
    0.41
     getS
    0.41
    Activations Density 6.673%

    No Known Activations