© 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. 14233
    Prev
    Next
    INDEX
    Explanations

    noun phrases connected by hyphens

    oai_token-act-pair · gemini-2.0-flash

    unusual or complex word patterns

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

    hyphen

    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
     A
    -0.81
     H
    -0.81
     Ar
    -0.79
     We
    -0.77
     My
    -0.76
     T
    -0.76
     I
    -0.73
     V
    -0.73
     B
    -0.73
     N
    -0.73
    POSITIVE LOGITS
     itſelf
    1.16
     crdi
    0.85
     poffible
    0.83
     uſed
    0.82
    ſelves
    0.81
     cdti
    0.81
     marinho
    0.80
     leſs
    0.79
     raiſ
    0.77
     faſt
    0.76
    Activations Density 2.327%

    No Known Activations