© 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. 2630
    Prev
    Next
    INDEX
    Explanations

    the word "Dark" and words associated with negative conditions

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "Dark"

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

    dark

    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
    httphttps
    -0.66
    twimg
    -0.63
     Roskov
    -0.61
    TargetException
    -0.59
    MemoryWarning
    -0.59
     оригіналу
    -0.58
    trino
    -0.57
    ArgsConstructor
    -0.57
    RegistryLite
    -0.57
    Lähteet
    -0.57
    POSITIVE LOGITS
    hljs
    0.56
    ened
    0.52
     souls
    0.49
     soul
    0.44
    asi
    0.44
    room
    0.44
     outer
    0.44
    heart
    0.43
     himo
    0.43
    Eksterne
    0.43
    Activations Density 0.769%

    No Known Activations