© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13072
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain parentheses and semicolons, particularly in the context of testing.

    oai_token-act-pair · gemini-2.0-flash

    punctuation and code block endings

    np_token-act-pair-logits · gpt-4o-mini

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    -0.84
     doubtnut
    -0.84
    .)}
    -0.83
     Monfieur
    -0.83
    "},
    -0.82
    )";
    -0.81
    OGND
    -0.79
    RepeatedField
    -0.78
     Theſe
    -0.78
    )");
    -0.76
    POSITIVE LOGITS
    ↵
    0.90
     the
    0.78
     el
    0.54
     de
    0.53
     in
    0.51
     s
    0.47
     res
    0.46
     đi
    0.45
     one
    0.44
     sur
    0.43
    Activations Density 1.625%

    No Known Activations