© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10892
    Prev
    Next
    INDEX
    Explanations

    proper nouns and adjectives, sometimes in a series

    oai_token-act-pair · gemini-2.0-flash

    descriptive 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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Signalez
    -0.71
     transfieras
    -0.66
    >--}}
    -0.61
    }{*}{}
    -0.60
    tieth
    -0.59
     TestBed
    -0.57
     Bourgoin
    -0.56
     CURIAM
    -0.56
    }-*/;
    -0.55
    ('');
    -0.54
    POSITIVE LOGITS
    存于互联网档案馆
    0.52
     People
    0.50
     Muscle
    0.47
     Love
    0.47
     Hearts
    0.46
     Feet
    0.46
     Hands
    0.45
     Minds
    0.45
     Carbon
    0.44
     Lemon
    0.44
    Activations Density 2.124%

    No Known Activations