© 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. 6203
    Prev
    Next
    INDEX
    Explanations

    sentences where the author is making an argument

    oai_token-act-pair · gemini-2.0-flash

    coding syntax or tags

    np_token-act-pair-logits · gpt-4o-mini
    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
    bootstrapcdn
    -0.47
    luan
    -0.45
     convertView
    -0.45
     MainAxisSize
    -0.43
    ANDRO
    -0.42
    resseur
    -0.42
     فريبيس
    -0.41
     Batal
    -0.41
    Wander
    -0.40
    ide
    -0.40
    POSITIVE LOGITS
    ^(@)
    0.70
    AddTagHelper
    0.68
    Personendaten
    0.66
    __*/
    0.65
    UnsafeEnabled
    0.61
    >--}}
    0.60
     moot
    0.60
    ברס
    0.60
     <=",
    0.60
    ReusableCell
    0.59
    Activations Density 1.706%

    No Known Activations