© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14782
    Prev
    Next
    INDEX
    Explanations

    positive descriptive adjectives

    oai_token-act-pair · gemini-2.0-flash

    positive descriptive snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     the
    -0.77
    :
    -0.62
     is
    -0.58
     of
    -0.56
    .
    -0.52
     it
    -0.52
     this
    -0.51
     on
    -0.50
     in
    -0.49
     at
    -0.48
    POSITIVE LOGITS
    StoryboardSegue
    1.02
    ,&
    0.93
     BoxFit
    0.90
     &___
    0.90
    ^(@)
    0.89
    IsContent
    0.84
     ,
    0.83
    StructEnd
    0.81
     TextInputType
    0.79
    AnimationsModule
    0.77
    Activations Density 5.389%

    No Known Activations