© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12370
    Prev
    Next
    INDEX
    Explanations

    conversational text, including internet chat shorthands

    oai_token-act-pair · gemini-2.0-flash

    Chat-like content

    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
    Fine
    -0.51
    fine
    -0.46
    CppMethod
    -0.46
    Good
    -0.43
     Fine
    -0.42
    IsContent
    -0.42
    FINE
    -0.41
    we
    -0.40
    you
    -0.39
     Celui
    -0.39
    POSITIVE LOGITS
     Roskov
    0.76
    ]";
    0.69
    makeConstraints
    0.69
    ^(@)
    0.69
     ویکی‌پدیا
    0.67
    BibitemShut
    0.66
    verwijspagina
    0.66
    bibinfo
    0.66
    lapsingToolbar
    0.65
    ')")
    0.65
    Activations Density 10.862%

    No Known Activations