© 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. 6297
    Prev
    Next
    INDEX
    Explanations

    code and French and Samoan language

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms or attributes

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

    Code and chat 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
    ագրություններ
    -0.86
     صوتيه
    -0.62
    lgari
    -0.55
    migrationBuilder
    -0.55
     internetowa
    -0.53
    География
    -0.52
     Trident
    -0.52
    ￡
    -0.51
    czeń
    -0.51
     trident
    -0.50
    POSITIVE LOGITS
    InjectAttribute
    0.54
    tinyos
    0.52
    PreferredItem
    0.51
    WriteTagHelper
    0.49
    UnusedPrivate
    0.49
    Personendaten
    0.48
    angal
    0.48
     NSCoder
    0.47
     Infórmanos
    0.47
     weren
    0.47
    Activations Density 0.834%

    No Known Activations