© 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. 6120
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "be" and contractions involving "be."

    oai_token-act-pair · gemini-2.0-flash

    adjectives describing personality traits

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

    be/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
     TestBed
    -0.65
    DeleteBehavior
    -0.62
    openSession
    -0.62
    AutoScaleMode
    -0.59
    فحة
    -0.57
     Administrativna
    -0.56
     autorytatywna
    -0.52
    ########.
    -0.52
    uitable
    -0.52
    mybatisplus
    -0.51
    POSITIVE LOGITS
     intelligent
    0.56
     clever
    0.56
     greedy
    0.56
    HAVE
    0.56
     creative
    0.56
    ="@+
    0.55
     melo
    0.54
     truthful
    0.53
     verbose
    0.53
     selfish
    0.52
    Activations Density 0.889%

    No Known Activations