© 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. 7943
    Prev
    Next
    INDEX
    Explanations

    instances of "is", "its", "of", "due to", "as well as", and numbers

    oai_token-act-pair · gemini-2.0-flash

    describing attributes

    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
     Their
    -1.26
    Their
    -1.18
     Your
    -0.98
    your
    -0.97
    Your
    -0.95
     deras
    -0.92
     mijn
    -0.92
    YOUR
    -0.91
     deres
    -0.89
    themselves
    -0.89
    POSITIVE LOGITS
     is
    1.21
     has
    0.65
     it
    0.65
    is
    0.65
     there
    0.64
     isFirst
    0.60
     isComment
    0.56
     they
    0.54
    makeText
    0.54
     isn
    0.52
    Activations Density 35.783%

    No Known Activations