© 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. 2999
    Prev
    Next
    INDEX
    Explanations

    code blocks involving box measurements and padding calculations

    oai_token-act-pair · gemini-2.0-flash

    0

    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
    ReusableCell
    -0.92
    TagHelper
    -0.91
    LookAnd
    -0.90
     Monfieur
    -0.90
     kaarangay
    -0.88
     transfieras
    -0.88
     myſelf
    -0.88
     whoſe
    -0.85
    Personendaten
    -0.84
     Roskov
    -0.83
    POSITIVE LOGITS
    0.52
    					
    0.48
                                   
    0.43
    c
    0.43
    </em>
    0.43
    Javadoc
    0.43
              
    0.43
    #
    0.42
    </strong>
    0.41
    Ã
    0.40
    Activations Density 1.127%
    No Known Activations