© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6873
    Prev
    Next
    INDEX
    Explanations

    clauses within legal or technical documents

    oai_token-act-pair · gemini-2.0-flash

    programming or data structure keywords

    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
    .$,
    -0.65
    .},
    -0.63
    /}.
    -0.61
    $).
    -0.59
    .",
    -0.58
    ".
    -0.56
    騨
    -0.56
    archiviato
    -0.56
    }.
    -0.54
    }$.
    -0.54
    POSITIVE LOGITS
    ValueStyle
    0.64
     propOrder
    0.63
    Enllaces
    0.54
    Demografía
    0.51
    addCriterion
    0.50
    anément
    0.49
    oneofs
    0.48
    LookAnd
    0.45
    enderror
    0.44
    TableAdapter
    0.44
    Activations Density 7.850%

    No Known Activations