© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5689
    Prev
    Next
    INDEX
    Explanations

    code and code-like-syntax.

    oai_token-act-pair · gemini-2.0-flash

    diverse foreign language tokens

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

    foreign words

    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
     association
    -1.12
     associations
    -0.85
     associated
    -0.85
     associate
    -0.81
    association
    -0.80
     associating
    -0.78
     assoc
    -0.77
     asoci
    -0.77
    Association
    -0.76
     associates
    -0.76
    POSITIVE LOGITS
    PASO
    0.56
     intptr
    0.55
     افتراض
    0.48
    ntomas
    0.46
    Bước
    0.45
     naviguant
    0.44
    իվ
    0.43
    topt
    0.42
     commerciales
    0.42
     cliquant
    0.42
    Activations Density 1.530%

    No Known Activations