© 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. 7164
    Prev
    Next
    INDEX
    Explanations

    words related to the features and usage of a pillow

    oai_token-act-pair · gemini-2.0-flash

    technical or specialized terms

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

    bed, sleeping

    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
    StoryboardSegue
    -0.72
    MessageOf
    -0.69
    ReusableCell
    -0.69
    клопе
    -0.63
     BoxFit
    -0.60
    adə
    -0.59
     Himo
    -0.58
    utilisons
    -0.58
     lenker
    -0.58
    TabStop
    -0.58
    POSITIVE LOGITS
    quef
    0.51
    specialchars
    0.50
    ụng
    0.48
    othelioma
    0.47
    lietta
    0.47
    GenerationType
    0.46
     compression
    0.45
     engineering
    0.45
    chen
    0.45
    áñez
    0.43
    Activations Density 5.536%

    No Known Activations