© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10147
    Prev
    Next
    INDEX
    Explanations

    code-related terms, especially in Spanish

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    PrototypeOf
    -0.54
     I
    -0.54
    Cho
    -0.53
     surla
    -0.52
     Cho
    -0.51
     myſelf
    -0.50
     myself
    -0.50
     насељу
    -0.49
    لمانيا
    -0.48
    bibinfo
    -0.48
    POSITIVE LOGITS
    padek
    0.63
     manquante
    0.53
     liberi
    0.51
     couverte
    0.51
    scales
    0.50
    Personensuche
    0.50
    AutoScaleMode
    0.48
     actionTypes
    0.48
     tačiau
    0.47
    arel
    0.47
    Activations Density 0.224%

    No Known Activations