© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 9644
    Prev
    Next
    INDEX
    Explanations

    words or phrases that could be considered descriptive in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks and conjunctions

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

    adjectives

    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
     []),
    -0.87
    /**
    -0.76
    ChildScrollView
    -0.74
    '):
    
    -0.70
    }',
    -0.70
     antaranya
    -0.69
     ''),
    -0.69
    "):
    
    -0.68
    ."],
    -0.68
    ...");
    
    -0.67
    POSITIVE LOGITS
    ,
    2.23
    ,
    0.63
     but
    0.61
    ،
    0.59
     ,
    0.54
    、
    0.54
    ImageContext
    0.51
    ,\
    0.47
    but
    0.44
    _,
    0.42
    Activations Density 3.196%

    No Known Activations