© 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. 8179
    Prev
    Next
    INDEX
    Explanations

    words that describe an event or story

    oai_token-act-pair · gemini-2.0-flash

    specific methods or arrangements

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

    methods

    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
     giudi
    -0.66
     colère
    -0.63
     femininas
    -0.63
     suivantes
    -0.63
     poussière
    -0.61
     especiais
    -0.60
     frumo
    -0.59
    RectangleBorder
    -0.59
     suivants
    -0.58
    ✨:
    -0.58
    POSITIVE LOGITS
     but
    0.74
    ,
    0.66
     method
    0.64
     arrangement
    0.61
     assumption
    0.60
     tactic
    0.59
     propOrder
    0.59
     piece
    0.59
    assumption
    0.59
     clue
    0.58
    Activations Density 11.273%

    No Known Activations