© 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. 7108
    Prev
    Next
    INDEX
    Explanations

    words related to experimental results, food storage, and social events

    oai_token-act-pair · gemini-2.0-flash

    freezing and preservation methods

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

    freezing

    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
     suor
    -0.45
    SqlClient
    -0.45
    URRED
    -0.43
     lesión
    -0.43
     schlä
    -0.43
    ceton
    -0.42
     loue
    -0.42
     fédé
    -0.42
    asztal
    -0.42
     fysis
    -0.42
    POSITIVE LOGITS
     frozen
    0.96
     froze
    0.88
     freeze
    0.87
     freezer
    0.86
     freezing
    0.82
     Freeze
    0.82
     Freezing
    0.79
    frozen
    0.79
     thawing
    0.77
    freeze
    0.75
    Activations Density 3.234%

    No Known Activations