© 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. 12117
    Prev
    Next
    INDEX
    Explanations

    negative sentiments, complaints, and strong opinions, possibly within quotes.

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages/technical issues

    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
     â
    -2.31
    â
    -2.13
    Â
    -2.09
     �
    -1.95
     
    -1.91
     Â
    -1.74
    �
    -1.71
     &#
    -1.61
     

    -1.57
     Ã
    -1.55
    POSITIVE LOGITS
    省市镇
    0.60
    etheless
    0.54
    שְׁ
    0.50
    %";
    0.50
    -}
    0.49
    Ữ
    0.48
    Britannique
    0.48
     Wiktionnaire
    0.45
    énario
    0.44
     سكانية
    0.44
    Activations Density 7.354%

    No Known Activations