© 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. 3312
    Prev
    Next
    INDEX
    Explanations

    a combination of the word "the" and emotionally charged language

    oai_token-act-pair · gemini-2.0-flash

    terms related to clarity and truth

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

    the

    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
     also
    -0.45
     anche
    -0.45
     even
    -0.43
     we
    -0.42
    ,
    -0.42
     as
    -0.38
    rend
    -0.38
    лото
    -0.38
     temos
    -0.37
     sebagai
    -0.36
    POSITIVE LOGITS
     disambiguazione
    0.95
     fact
    0.84
     <<<<<<<<<<<<<<
    0.82
     truth
    0.81
     purpoſe
    0.79
    ^(@
    0.78
    ^(@)
    0.76
     itſelf
    0.76
     ſind
    0.73
     autorytatywna
    0.73
    Activations Density 1.925%

    No Known Activations