© 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. 8127
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Category" related to sports or historical groups

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act-logits · gemini-2.0-flash

    :

    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_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
     purpoſe
    -1.07
     pleaſure
    -1.05
     itſelf
    -1.04
     myſelf
    -0.99
     reaſon
    -0.98
     themſelves
    -0.96
     himſelf
    -0.94
     ſtate
    -0.94
     raiſ
    -0.94
    ſelf
    -0.94
    POSITIVE LOGITS
     vi
    0.24
     sa
    0.24
     il
    0.23
     la
    0.21
     im
    0.20
     den
    0.20
     si
    0.20
     qu
    0.20
     di
    0.19
     th
    0.19
    Activations Density 18.079%

    No Known Activations