© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4557
    Prev
    Next
    INDEX
    Explanations

    the word "offer" or a related form

    oai_token-act-pair · gemini-2.0-flash

    various forms of the word "offer"

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

    offer

    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
     donné
    -0.61
     donnée
    -0.52
     Provided
    -0.51
    Notae
    -0.51
     offered
    -0.50
    Hozzáférés
    -0.49
    AutoScaleMode
    -0.49
     forn
    -0.49
    ագրություններ
    -0.49
    roveň
    -0.48
    POSITIVE LOGITS
     a
    0.91
     an
    0.82
     the
    0.78
     another
    0.71
     some
    0.68
     us
    0.68
     these
    0.64
     plenty
    0.63
    AccessorTable
    0.62
    ///</
    0.59
    Activations Density 2.732%

    No Known Activations