© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 16357
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to societal issues, future events, literature, relationship status or object oriented programming

    oai_token-act-pair · gemini-2.0-flash

    Code-related syntax

    np_max-act-logits · gemini-2.0-flash

    say "punctuation"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    appoint
    -0.51
     Spots
    -0.51
     ویکی‌پدی
    -0.50
     nuis
    -0.50
     dépass
    -0.49
    άνι
    -0.49
     Mounts
    -0.48
    pazität
    -0.48
     ISTAT
    -0.48
     Earned
    -0.48
    POSITIVE LOGITS
    "));
    
    1.13
    ";
    
    1.08
    "}
    1.04
    '));
    
    1.04
    "))
    1.04
    )”.
    1.03
    ';
    
    1.02
    ”.
    1.01
    )".
    1.00
    ’.”
    1.00
    Activations Density 13.426%

    No Known Activations