© 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. 7797
    Prev
    Next
    INDEX
    Explanations

    pronouns and time related words

    oai_token-act-pair · gemini-2.0-flash

    Something happens

    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
     come
    -1.24
    come
    -1.14
     happen
    -1.09
    Come
    -1.04
    happen
    -0.97
    COME
    -0.93
     Come
    -0.92
     COME
    -0.90
     occur
    -0.85
     become
    -0.82
    POSITIVE LOGITS
    ungsver
    0.54
    wieś
    0.53
    igné
    0.53
    UnusedPrivate
    0.53
     educativas
    0.52
     ORM
    0.51
    WebElementEntity
    0.51
     StatefulWidget
    0.51
     esterni
    0.51
     CURIAM
    0.50
    Activations Density 4.489%

    No Known Activations