© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3715
    Prev
    Next
    INDEX
    Explanations

    words related to engineering, marketing, and research domains

    oai_token-act-pair · gemini-2.0-flash

    terms associated with engineering

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

    engineering marketing

    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
    IsMutable
    -0.74
    Tikang
    -0.72
     doubtnut
    -0.71
     />";
    -0.69
     Illy
    -0.68
    }$​
    -0.68
    ThroughAttribute
    -0.66
     altars
    -0.64
     cdti
    -0.64
    SharedDtor
    -0.63
    POSITIVE LOGITS
     U
    0.49
     res
    0.48
     \
    0.46
    textTheme
    0.45
    U
    0.43
     mano
    0.42
    OGND
    0.42
    LLocation
    0.42
    unik
    0.41
    hrens
    0.41
    Activations Density 4.774%

    No Known Activations