© 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. 1156
    Prev
    Next
    INDEX
    Explanations

    the word "to"

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    ArgumentParser
    -0.59
     and
    -0.53
    клопе
    -0.51
    .'-
    -0.51
     on
    -0.51
     in
    -0.51
    '],
    -0.50
    s
    -0.49
     **/
    -0.49
    '
    -0.49
    POSITIVE LOGITS
     the
    1.05
     your
    0.67
     their
    0.67
     a
    0.66
     his
    0.64
     our
    0.62
    ьаж
    0.60
    IVEREF
    0.56
    the
    0.55
     its
    0.55
    Activations Density 11.224%

    No Known Activations