© 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. 4661
    Prev
    Next
    INDEX
    Explanations

    specific parts of a code file, potentially related to Kotlin PSI elements

    oai_token-act-pair · gemini-2.0-flash

    programming syntax operators or structures

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

    code snippets

    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
     ->
    -1.43
    ->
    -1.24
    ->{
    -1.05
    ()->
    -0.99
    )->
    -0.94
    ]->
    -0.84
    ->$
    -0.84
    ))->
    -0.82
    ->_
    -0.77
    _->
    -0.77
    POSITIVE LOGITS
    _=
    0.50
    ^=
    0.49
    пись
    0.47
    AndEndTag
    0.47
    ništ
    0.47
    늘
    0.46
    }=
    0.46
     UIFont
    0.44
    ivamente
    0.42
    %=
    0.42
    Activations Density 1.137%

    No Known Activations