© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    lists of things, especially those related to science fiction or conventions

    oai_token-act-pair · gemini-2.0-flash

    scientific research papers

    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
    </i>
    -0.99
     first
    -0.91
     â
    -0.81
     fin
    -0.81
    first
    -0.81
    </b>
    -0.75
    â
    -0.75
    fin
    -0.74
     fi
    -0.71
    <i>
    -0.70
    POSITIVE LOGITS
     sign
    1.59
     Sign
    1.19
     di
    0.98
     SIGN
    0.98
    sign
    0.96
    Sign
    0.95
     dif
    0.85
    
    0.85
    sig
    0.84
     EconPapers
    0.83
    Activations Density 8.125%

    No Known Activations