© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12291
    Prev
    Next
    INDEX
    Explanations

    the letters "A", "The", and words followed by numbers, and a general sense of the start of something (like A nice comment)

    oai_token-act-pair · gemini-2.0-flash

    A

    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
    \{\\
    -0.57
     uſ
    -0.52
     myſelf
    -0.52
     another
    -0.51
     uſed
    -0.50
     others
    -0.49
     houſe
    -0.49
    Bibliograf
    -0.48
     diſt
    -0.47
     Efq
    -0.47
    POSITIVE LOGITS
    .
    0.69
    Is
    0.69
    while
    0.64
    ming
    0.60
     financières
    0.59
    was
    0.59
    ELF
    0.58
    Im
    0.58
    FT
    0.57
     redor
    0.57
    Activations Density 4.801%

    No Known Activations