© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11879
    Prev
    Next
    INDEX
    Explanations

    numbers and characters within scientific notation, figures, tables, chemical formulas or statistical equations

    oai_token-act-pair · gemini-2.0-flash

    Code and formulas

    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
     Initialized
    -0.59
     CreateTagHelper
    -0.52
     برانيه
    -0.52
    ViewFeatures
    -0.51
     themſelves
    -0.50
     himſelf
    -0.49
     enfans
    -0.48
    guisement
    -0.47
     ſtand
    -0.46
    tovat
    -0.46
    POSITIVE LOGITS
     }}}
    0.93
    }&
    0.86
    ]&
    0.85
    "]));
    0.85
     ]}
    0.84
    …)
    0.83
    ]}
    0.82
    ]_
    0.81
    …).
    0.81
    "}>
    0.80
    Activations Density 10.026%

    No Known Activations