© 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. 8819
    Prev
    Next
    INDEX
    Explanations

    source code and markup snippets along with some related terminology such as types string functions and datatypes

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    <eos>
    -0.18
      
    -0.14
    ↵
    -0.09
    -
    -0.08
    ↵↵
    -0.08
    ...
    -0.07
    -0.07
    </strong>
    -0.06
        
    -0.06
    …
    -0.06
    POSITIVE LOGITS
     myſelf
    1.98
     Efq
    1.91
     itſelf
    1.89
     Monfieur
    1.85
     ―――――
    1.77
     raiſ
    1.76
     Jefus
    1.71
     Theſe
    1.70
    ſelf
    1.69
     pleaſure
    1.69
    Activations Density 19.046%
    No Known Activations