© 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. 3128
    Prev
    Next
    INDEX
    Explanations

    code syntax and import statements

    oai_token-act-pair · gemini-2.0-flash

    say "from"

    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
     itſelf
    -1.06
    .")
    -1.05
    )";
    -1.01
    "):
    -0.98
    $")
    -0.96
    %")
    -0.94
    ьаж
    -0.92
     photolibrary
    -0.91
    "]));
    -0.91
     iſt
    -0.90
    POSITIVE LOGITS
     From
    0.77
    From
    0.72
    from
    0.68
     from
    0.68
     FROM
    0.60
     ,
    0.58
                    
    0.56
    FROM
    0.55
     &&
    0.55
     With
    0.55
    Activations Density 2.785%

    No Known Activations