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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6949
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, questions, and expressions of uncertainty or feeling.

    oai_token-act-pair · gemini-2.0-flash

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    makaian
    -0.44
     halv
    -0.44
    ready
    -0.43
    kook
    -0.42
     coisa
    -0.42
    vensko
    -0.42
     Ready
    -0.40
    coef
    -0.40
     εί
    -0.39
     SOP
    -0.39
    POSITIVE LOGITS
     متعلقه
    1.02
    脚注の使い方
    1.02
     Majefty
    0.92
    Personendaten
    0.90
    RegressionTest
    0.89
     itſelf
    0.88
    featureID
    0.84
    ſelf
    0.84
    ſelves
    0.81
    IsMutable
    0.81
    Activations Density 3.880%

    No Known Activations