© 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. 1145
    Prev
    Next
    INDEX
    Explanations

    trailing periods or words relating to effort and resources

    oai_token-act-pair · gemini-2.0-flash

    Beginning of content

    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
     taking
    -1.28
     hitting
    -1.18
     putting
    -1.16
     getting
    -1.16
     replacing
    -1.14
     creating
    -1.13
     dropping
    -1.09
     releasing
    -1.09
     bringing
    -1.09
     making
    -1.08
    POSITIVE LOGITS
    ंदीखरीदारी
    0.58
     Grüsse
    0.57
    Према
    0.55
    BeginContext
    0.50
    alignSelf
    0.50
    >//
    0.50
    Árbitro
    0.50
    WireFormat
    0.49
     maka
    0.48
    RefNanny
    0.48
    Activations Density 3.547%

    No Known Activations