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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5440
    Prev
    Next
    INDEX
    Explanations

    snippets of code and error messages

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks at the end of sentences

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

    used

    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
    =$?
    -0.51
    :')
    -0.45
     ());
    -0.44
    ghijklmnop
    -0.44
     }}$}
    -0.44
    …).
    -0.43
     ').
    -0.43
     }).
    -0.42
    ГЛА
    -0.42
    ?).
    -0.42
    POSITIVE LOGITS
    .-
    1.05
    .,
    1.05
    .",
    1.01
    .),
    0.96
    .;
    0.95
    ./
    0.93
    .=
    0.86
    .";
    0.85
    .',
    0.85
    @[+][
    0.85
    Activations Density 6.190%

    No Known Activations