© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11440
    Prev
    Next
    INDEX
    Explanations

    forms of "be" indicating a state of existence

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating identity or roles

    np_token-act-pair-logits · gpt-4o-mini

    being

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AutoScaleMode
    -0.83
     cherchés
    -0.82
    ConstraintMaker
    -0.78
    ########.
    -0.77
    BagConstraints
    -0.74
    #+#
    -0.73
     виправивши
    -0.73
    expandindo
    -0.73
     Мексичка
    -0.71
     kasarigan
    -0.71
    POSITIVE LOGITS
     part
    0.57
     a
    0.53
     sisi
    0.48
    /*
    0.47
     in
    0.46
     surrounded
    0.45
     responsive
    0.44
     with
    0.44
    awtextra
    0.43
     effective
    0.42
    Activations Density 4.694%

    No Known Activations