© 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. 5618
    Prev
    Next
    INDEX
    Explanations

    code or programming snippets including parameters, objects, and event handlers

    oai_token-act-pair · gemini-2.0-flash

    programming constructs or structures

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

    Programming 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
     nakalista
    -0.71
    tagHelperRunner
    -0.60
    Malformed
    -0.60
     lietu
    -0.58
     nationaux
    -0.57
    Lähteet
    -0.57
    IsContent
    -0.57
     RSSSF
    -0.55
     habet
    -0.53
    protoimpl
    -0.52
    POSITIVE LOGITS
    ScopeManager
    0.66
     postIndex
    0.57
    клопе
    0.54
    ]})
    0.52
    ceeding
    0.52
    #+#
    0.51
    felves
    0.51
     doInBackground
    0.51
    ++];
    0.51
    dataProvider
    0.51
    Activations Density 1.586%

    No Known Activations