© 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. 5731
    Prev
    Next
    INDEX
    Explanations

    a variety of pronouns and prepositions

    oai_token-act-pair · gemini-2.0-flash

    have

    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
    awtextra
    -0.59
    Had
    -0.55
     Had
    -0.55
     gehad
    -0.53
     Having
    -0.52
    oporosis
    -0.51
    )))));
    -0.50
    DotNetBar
    -0.49
    '};
    -0.49
    Having
    -0.49
    POSITIVE LOGITS
     have
    1.68
    have
    1.34
     has
    1.33
    Have
    1.30
     Have
    1.20
    has
    1.01
     HAVE
    0.96
     telah
    0.93
     đã
    0.91
     haue
    0.90
    Activations Density 9.967%

    No Known Activations