© 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. 10558
    Prev
    Next
    INDEX
    Explanations

    dense math and scientific text

    oai_token-act-pair · gemini-2.0-flash

    equations and math

    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
    httphttps
    -0.71
    PreferredItem
    -0.69
    下载附件
    -0.69
    rungsseite
    -0.68
    complexContent
    -0.67
    IntoConstraints
    -0.63
    TypedDataSet
    -0.59
    Einzelnachweise
    -0.57
     كومونز
    -0.57
    لينكات
    -0.56
    POSITIVE LOGITS
    guien
    0.54
     '>=
    0.54
    ]';
    0.54
     Ambos
    0.53
     contigo
    0.52
    htë
    0.51
     stanovnika
    0.51
     göm
    0.51
    )++;
    0.50
     Nemesis
    0.50
    Activations Density 11.332%

    No Known Activations