© 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. 4981
    Prev
    Next
    INDEX
    Explanations

    code snippets or other uses of math notation

    oai_token-act-pair · gemini-2.0-flash

    programming syntax and functions

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

    code

    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
    addGap
    -0.79
    migrationBuilder
    -0.68
    araj
    -0.57
    ]")]
    -0.56
    colgroup
    -0.56
    }],
    -0.55
     ISNI
    -0.54
     öss
    -0.54
     аса
    -0.54
    ardians
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.72
    DoubleQuotes
    0.66
    WriteBarrier
    0.56
     مرئيه
    0.56
    antaine
    0.49
    Werdegang
    0.45
    LookAnd
    0.44
     ETI
    0.43
    "।
    0.42
    Описание
    0.42
    Activations Density 3.988%

    No Known Activations