© 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. 141
    Prev
    Next
    INDEX
    Explanations

    start-of-line whitespace and numbers, as well as syntax and punctuation

    oai_token-act-pair · gemini-2.0-flash

    Code 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
     Efq
    -1.21
     myſelf
    -1.14
     itſelf
    -1.07
     $_"
    -1.06
     Jefus
    -1.01
     raiſ
    -0.99
     himſelf
    -0.99
     dreamstime
    -0.98
     doubtnut
    -0.98
     uſed
    -0.96
    POSITIVE LOGITS
     I
    0.66
    :
    0.62
     s
    0.59
    -
    0.56
    <eos>
    0.55
     V
    0.55
     _
    0.55
     i
    0.54
     l
    0.54
    !
    0.54
    Activations Density 1.969%

    No Known Activations