© 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. 11802
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express emotion, particularly positive ones

    oai_token-act-pair · gemini-2.0-flash

    Intense emotions

    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
     pure
    -0.57
     Pure
    -0.50
     excitement
    -0.48
     expectation
    -0.47
     anticipation
    -0.47
     PURE
    -0.46
    ախ
    -0.46
    ραγ
    -0.45
     utter
    -0.44
     transférez
    -0.44
    POSITIVE LOGITS
     kasarigan
    0.89
    Хьажоргаш
    0.69
    новниш
    0.68
    principalColumn
    0.66
     gynhyrchwyd
    0.65
     समीक्षक
    0.63
     HasFactory
    0.61
    HtmlAttribute
    0.61
    IsMutable
    0.60
    __':
    0.60
    Activations Density 8.113%

    No Known Activations