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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9489
    Prev
    Next
    INDEX
    Explanations

    a mix of phrases from legal documents, political opinions, and scientific papers that often include words like "that", "is", and conjunctions.

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

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

    Punctuation marks

    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
    UserScript
    -0.91
    ChildScrollView
    -0.91
    ]--;
    -0.81
    NUMX
    -0.81
    '';
    -0.78
     saites
    -0.78
    findpost
    -0.77
     محفوظة
    -0.76
    مصادر
    -0.74
    তথ্যসূত্র
    -0.74
    POSITIVE LOGITS
    ,
    2.56
    ，
    0.83
    ،
    0.76
    、
    0.67
     ,
    0.66
    (),
    0.59
    ,\
    0.56
    ,
    0.51
    .,
    0.51
    ,(
    0.51
    Activations Density 7.137%

    No Known Activations