© 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. 5581
    Prev
    Next
    INDEX
    Explanations

    snippets of code or calculation

    oai_token-act-pair · gemini-2.0-flash

    words in foreign or technical context

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

    computer 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
     $
    -1.84
     ($
    -1.55
    ($
    -1.54
    -$
    -1.53
    /$
    -1.47
    =$
    -1.45
    {$
    -1.45
    $
    -1.43
     "$
    -1.42
    :$
    -1.41
    POSITIVE LOGITS
    ̣ng
    0.50
    PreferredItem
    0.46
     ddelweddau
    0.42
    uksessa
    0.42
     mosso
    0.41
    verarbeitung
    0.41
    ựa
    0.40
    ztő
    0.40
    verley
    0.40
    Lieferumfang
    0.40
    Activations Density 1.917%

    No Known Activations