© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 309
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and characters that look like URLs or DOIs

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    )))));
    -0.56
    
    -0.53
     tantôt
    -0.51
     respectivement
    -0.50
     unlike
    -0.49
     sauvage
    -0.49
     vertes
    -0.48
     cinematogra
    -0.47
     pêche
    -0.46
    ,
    -0.45
    POSITIVE LOGITS
    zzleHttp
    0.71
     NSCoder
    0.70
    TagMode
    0.70
     EClass
    0.64
     CanadaChoose
    0.63
    rungsseite
    0.60
    hdashline
    0.60
    WaitGroup
    0.59
     tartalomajánló
    0.59
     HttpHeaders
    0.57
    Activations Density 0.348%

    No Known Activations