© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8836
    Prev
    Next
    INDEX
    Explanations

    figure and table references in scientific papers

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -1.18
     myſelf
    -1.04
     Efq
    -1.02
     becauſe
    -0.99
     Theſe
    -0.97
     Monfieur
    -0.96
     ſeveral
    -0.94
     Majefty
    -0.91
     purpoſe
    -0.90
     poffible
    -0.90
    POSITIVE LOGITS
    </strong>
    1.38
    ↵↵
    1.35
     
    1.31
    </b>
    1.28
    </h4>
    1.28
    .
    1.27
    </h3>
    1.27
    </em>
    1.24
    ↵
    1.23
    -
    1.23
    Activations Density 11.023%

    No Known Activations