© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10695
    Prev
    Next
    INDEX
    Explanations

    code syntax and mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    code/math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     —
    -1.18
    }}^
    -1.14
    }^
    -1.09
     —,
    -0.96
    }}_
    -0.96
    })^
    -0.92
    ]^
    -0.91
    '^
    -0.88
    )^
    -0.87
    }^\
    -0.87
    POSITIVE LOGITS
     أيضاً
    1.05
    <u>
    1.03
    LOGGER
    1.02
     �
    0.94
    য়ে
    0.93
     
    0.89
    �
    0.88
    ്‍
    0.85
     　
    0.85
    ^{
    0.78
    Activations Density 3.516%

    No Known Activations