© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5621
    Prev
    Next
    INDEX
    Explanations

    names of people and companies

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code syntax

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

    Code snippets/technical 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_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
    intellij
    -0.44
     Bell
    -0.44
    øya
    -0.40
    <!--
    -0.40
    
    -0.40
    metr
    -0.40
    locu
    -0.40
    agie
    -0.40
     mato
    -0.40
    Sco
    -0.39
    POSITIVE LOGITS
     الحره
    0.69
     ब्रेकडाउन
    0.66
    StructEnd
    0.66
     виправивши
    0.66
    +:+
    0.65
    Carcinogenicity
    0.63
    :✨
    0.60
    invokeLater
    0.59
     riuscito
    0.59
    deep
    0.58
    Activations Density 1.140%

    No Known Activations