© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9682
    Prev
    Next
    INDEX
    Explanations

    a mishmash of discourse markers, parenthetical punctuation, and personal pronouns and possessives.

    oai_token-act-pair · gemini-2.0-flash

    webpage text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    /');
    -0.60
    */].
    -0.59
    '],'
    -0.59
    VIAF
    -0.59
    mamm
    -0.56
    =");
    -0.55
    __);
    -0.53
    }`).
    -0.52
    */),
    -0.52
    });
    -0.51
    POSITIVE LOGITS
     lenker
    0.80
    Source
    0.66
     Watch
    0.63
     ujednoznacz
    0.63
    Text
    0.63
     Text
    0.61
     Read
    0.60
     Learn
    0.58
     Source
    0.58
    View
    0.57
    Activations Density 7.839%

    No Known Activations