© 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. 10568
    Prev
    Next
    INDEX
    Explanations

    mentions of the name Tony Inman, especially when surrounded by job titles or related words

    oai_token-act-pair · gemini-2.0-flash

    Articles and bios

    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
    ʰ
    -0.42
    Brainz
    -0.41
     кро
    -0.40
     taked
    -0.39
     contraintes
    -0.39
    ọa
    -0.39
    ној
    -0.39
    goog
    -0.38
    ภ
    -0.38
     eneste
    -0.38
    POSITIVE LOGITS
     صوتيه
    0.82
     nakalista
    0.82
    出版年
    0.72
    bkz
    0.65
     propOrder
    0.65
     Мексичка
    0.63
     ExecuteAsync
    0.62
    issor
    0.61
    setVerticalGroup
    0.59
    StoryboardSegue
    0.59
    Activations Density 7.671%

    No Known Activations