© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6149
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, references to books, and relationships

    oai_token-act-pair · gemini-2.0-flash

    expressions of affection or appreciation

    np_token-act-pair-logits · gpt-4o-mini

    Positive sentiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    InjectAttribute
    -0.72
    ParallelGroup
    -0.68
     Reverso
    -0.68
     useRouter
    -0.64
    writeField
    -0.59
     IndexPath
    -0.59
    JNIEnv
    -0.58
    IsContent
    -0.57
    SourceChecksum
    -0.56
    adpleegd
    -0.56
    POSITIVE LOGITS
     loved
    1.35
     liked
    1.20
     Loved
    1.16
     LOVED
    1.14
    loved
    1.10
    Loved
    1.06
     Liked
    0.97
     enjoyed
    0.95
    Enjoyed
    0.80
     adored
    0.78
    Activations Density 2.532%

    No Known Activations