Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10015
    Prev
    Next
    INDEX
    Explanations

    sentences describing a situation where someone is being observed or monitored

    oai_token-act-pair · gemini-2.0-flash

    synonyms for "back"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    DockStyle
    -0.79
     poffe
    -0.63
    جوايز
    -0.60
     TAMBIÉN
    -0.58
     beginnetje
    -0.57
     juſ
    -0.57
     chofe
    -0.57
     raiſ
    -0.57
    Население
    -0.56
    tonsoft
    -0.56
    POSITIVE LOGITS
     back
    1.68
     rear
    1.55
     behind
    1.55
    back
    1.55
     Back
    1.43
    behind
    1.40
     atrás
    1.39
    Back
    1.38
    BACK
    1.36
     belakang
    1.36
    Activations Density 0.789%

    No Known Activations