© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3214
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be."

    oai_token-act-pair · gemini-2.0-flash

    project completion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ьаж
    -0.75
     READY
    -0.70
     Ready
    -0.68
    READY
    -0.65
    Ready
    -0.62
    numerusform
    -0.60
    INSEE
    -0.59
    prone
    -0.59
    
    -0.58
     GONE
    -0.57
    POSITIVE LOGITS
    ufnahme
    0.56
    WebMethod
    0.53
    !*\
    0.49
    вного
    0.43
    iological
    0.42
    fono
    0.42
     NavController
    0.42
     under
    0.42
     inside
    0.42
    τεί
    0.42
    Activations Density 1.974%

    No Known Activations