© 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. 8875
    Prev
    Next
    INDEX
    Explanations

    sentences containing personal pronouns, especially when combined with auxiliary verbs or references to authority figures/groups.

    oai_token-act-pair · gemini-2.0-flash

    Taken

    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
     take
    -0.98
     takes
    -0.95
    take
    -0.92
     Take
    -0.92
    Take
    -0.89
    takes
    -0.81
     Takes
    -0.79
     TAKE
    -0.78
     taking
    -0.78
    TAKE
    -0.75
    POSITIVE LOGITS
     taken
    0.75
    TintMode
    0.75
     TO
    0.60
    ISupport
    0.60
     Taken
    0.54
     TAKEN
    0.54
    ADVERTISEMENT
    0.54
    Taken
    0.51
    mesin
    0.51
    __":
    0.50
    Activations Density 4.368%

    No Known Activations