© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2204
    Prev
    Next
    INDEX
    Explanations

    HTML markup tags with 'a' and 'p' along with words 'string', 'field', 'key', and 'value'

    oai_token-act-pair · gemini-2.0-flash

    HTML/XML 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    <
    -2.44
    >
    -1.51
     $<
    -1.51
     <
    -1.48
    )<
    -1.42
    }<
    -1.39
    .<
    -1.39
    <\
    -1.30
    ]<
    -1.30
    !<
    -1.28
    POSITIVE LOGITS
     ModelExpression
    0.67
    UnknownFieldSet
    0.63
     &___
    0.60
    math
    0.58
    ніципалі
    0.56
    gameserver
    0.56
     препратки
    0.54
    gouv
    0.54
    DoubleQuotes
    0.52
    MethodManager
    0.52
    Activations Density 3.883%

    No Known Activations