© 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. 5662
    Prev
    Next
    INDEX
    Explanations

    second person pronouns combined with auxiliary verbs such as "will" or "can."

    oai_token-act-pair · gemini-2.0-flash

    will/ll

    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
    >*/
    -0.64
     is
    -0.64
    uegos
    -0.59
    libft
    -0.55
    lear
    -0.51
    Found
    -0.50
    elt
    -0.49
    ValueStyle
    -0.49
    is
    -0.48
     iconTwitter
    -0.48
    POSITIVE LOGITS
     stirred
    0.62
     rained
    0.56
     الحره
    0.55
     tempted
    0.54
     offered
    0.53
     tackled
    0.52
     pierced
    0.51
    setupUi
    0.51
     reminded
    0.51
    jacency
    0.51
    Activations Density 4.548%

    No Known Activations