© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    the letter A, often as the first word in a sentence or phrase

    oai_token-act-pair · gemini-2.0-flash

    phrases starting with 'A'

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

    A

    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
     autorité
    -0.82
     affrontare
    -0.80
     identité
    -0.79
     amitié
    -0.79
     ***!
    -0.77
     poussière
    -0.77
     équilibre
    -0.76
     secours
    -0.76
     église
    -0.75
     énergie
    -0.75
    POSITIVE LOGITS
     few
    0.76
     lot
    0.67
     very
    0.63
     new
    0.63
     long
    0.59
     rare
    0.59
     close
    0.57
     popular
    0.56
     nice
    0.56
     couple
    0.55
    Activations Density 2.122%

    No Known Activations