© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11732
    Prev
    Next
    INDEX
    Explanations

    words related to assistance and novel attributes

    oai_token-act-pair · gemini-2.0-flash

    Support or original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.38
     itſelf
    -1.35
     ſtate
    -1.30
     ſche
    -1.26
     himſelf
    -1.23
     poffible
    -1.21
     raiſ
    -1.20
     themſelves
    -1.16
     purpoſe
    -1.15
     Shakspeare
    -1.13
    POSITIVE LOGITS
     to
    0.69
    ↵
    0.67
     '
    0.63
    ,
    0.60
    i
    0.58
    "
    0.57
     in
    0.56
     a
    0.56
     g
    0.56
     
    0.55
    Activations Density 0.420%

    No Known Activations