© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6026
    Prev
    Next
    INDEX
    Explanations

    words related to achieving positive results or good effects, and also to some extent diet/eating habits and risks.

    oai_token-act-pair · gemini-2.0-flash

    outcomes

    np_max-act · gemini-2.0-flash

    outcomes

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     
    -1.31
     (
    -1.16
     or
    -1.08
     a
    -1.05
     the
    -0.98
     [
    -0.96
     in
    -0.94
    ,
    -0.90
     "
    -0.90
    :
    -0.87
    POSITIVE LOGITS
     myſelf
    2.41
     Efq
    2.31
     Monfieur
    2.27
     itſelf
    2.22
     pleaſure
    2.22
     purpoſe
    2.20
     houſe
    2.17
     Jefus
    2.16
     himſelf
    2.13
     Majefty
    2.08
    Activations Density 2.430%

    No Known Activations