© 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. 12898
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    code syntax and structure

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

    say bracket 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_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
    ))
    -1.34
    ））
    -1.26
    "))
    -1.19
    )).
    -1.14
    '))
    -1.12
    .))
    -1.09
    ))
    -0.99
    "));
    -0.99
    ")).
    -0.99
    )):
    -0.98
    POSITIVE LOGITS
    )";
    0.80
     ")";
    0.76
     "]";
    0.71
    )";
    0.65
    }();
    0.64
    )';
    0.60
     />";
    0.59
    KommentareTeilen
    0.57
     },
    0.53
    }";
    0.52
    Activations Density 1.329%

    No Known Activations