© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6220
    Prev
    Next
    INDEX
    Explanations

    instances of actions involving filling things or making selections

    oai_token-act-pair · gemini-2.0-flash

    text with a focus on filling or filling-related actions

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

    say "with"

    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
     Full
    -0.47
     Kammer
    -0.45
    enosine
    -0.45
     full
    -0.43
    Full
    -0.43
     يتيمه
    -0.41
    full
    -0.41
     pass
    -0.40
    diğini
    -0.39
     Do
    -0.39
    POSITIVE LOGITS
    __":
    
    0.81
     AssemblyTitle
    0.75
     المعيارى
    0.71
     ContentValues
    0.66
    GIVEREF
    0.66
    __':
    
    0.65
    XmlAccessType
    0.65
     typelib
    0.65
     Италијани
    0.63
     تضيفلها
    0.60
    Activations Density 6.769%

    No Known Activations