© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6612
    Prev
    Next
    INDEX
    Explanations

    a combination of articles ("the") and adjectives/nouns that indicate relative position, importance or time.

    oai_token-act-pair · gemini-2.0-flash

    notable moments in a narrative

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

    significant moments

    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
    tvguidetime
    -0.60
    Notae
    -0.56
     незавершена
    -0.55
    Jereo
    -0.54
     BufferedReader
    -0.54
    featureID
    -0.54
     SafeMath
    -0.54
    ᅠ
    -0.53
    Rujuakan
    -0.52
     Curi
    -0.52
    POSITIVE LOGITS
     turning
    0.65
     moment
    0.60
    })));
    0.57
    moment
    0.56
    }));
    
    0.51
    BECK
    0.50
    PostConstruct
    0.50
    PageRoute
    0.49
     pièce
    0.48
    Moment
    0.48
    Activations Density 1.813%

    No Known Activations