© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    Arabic names that include "Al" or names including initials

    oai_token-act-pair · gemini-2.0-flash

    names with 'Al' prefix

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

    Names and identifiers

    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
     :
    -0.57
    :~
    -0.54
     requestCode
    -0.54
    ~:
    -0.52
    nagel
    -0.50
     الرياضيه
    -0.49
    verkehr
    -0.47
    Bioaccumulative
    -0.47
     Colonies
    -0.46
    úrate
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.59
     المعيارى
    0.58
    expandindo
    0.58
    PMailer
    0.57
    principalTable
    0.57
    SerializedSize
    0.57
    "}"
    0.54
    تقاوى
    0.52
    reciation
    0.51
     Roskov
    0.51
    Activations Density 0.437%

    No Known Activations