© 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. 6376
    Prev
    Next
    INDEX
    Explanations

    expressions of grief and memory and also comments that are short and separated from the rest of the text by spacing

    oai_token-act-pair · gemini-2.0-flash

    diverse and foreign language terms

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

    End of sentence/statement

    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
    labelledby
    -0.49
    WEATHER
    -0.49
    breeze
    -0.47
    αι
    -0.47
     IEnumerator
    -0.46
    yt
    -0.46
    //
    -0.45
    atina
    -0.45
    setTypeface
    -0.45
    Errorf
    -0.44
    POSITIVE LOGITS
    expandindo
    0.88
    ReusableCell
    0.84
     beginnetje
    0.70
    djangoproject
    0.68
     مشين
    0.68
     autorytatywna
    0.68
    ंदीखरीदारी
    0.66
    
    0.66
    Tikang
    0.65
     betweenstory
    0.65
    Activations Density 1.416%

    No Known Activations