© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10465
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing opinions on media

    oai_token-act-pair · gemini-2.0-flash

    positive/negative sentiment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    #
    -0.78
    saraba
    -0.71
    出版年
    -0.67
    webElementGuid
    -0.65
     مرئيه
    -0.65
    ❋
    -0.65
    WaitGroup
    -0.63
    ThroughAttribute
    -0.63
    mazoo
    -0.60
     للمعارف
    -0.60
    POSITIVE LOGITS
     positive
    2.11
    positive
    1.84
    Positive
    1.76
     Positive
    1.75
     negative
    1.73
     POSITIVE
    1.64
    Negative
    1.52
     positiva
    1.51
     positif
    1.51
    negative
    1.50
    Activations Density 3.502%

    No Known Activations