© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 508
    Prev
    Next
    INDEX
    Explanations

    subjective words and phrases expressing emotions and judgements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     houſe
    -0.99
     Houſe
    -0.91
     chré
    -0.89
     faſt
    -0.89
     Efq
    -0.85
     itſelf
    -0.84
     myſelf
    -0.83
     ſtate
    -0.82
     Anſ
    -0.82
     CreateTagHelper
    -0.81
    POSITIVE LOGITS
     po
    0.56
     Po
    0.48
     en
    0.46
     De
    0.46
     ad
    0.45
     ur
    0.45
     i
    0.43
     per
    0.43
     ag
    0.43
     em
    0.42
    Activations Density 3.573%

    No Known Activations