© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11943
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to making a claim or stating a hypothesis

    oai_token-act-pair · gemini-2.0-flash

    unproven ideas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Datuak
    -0.57
    ıntı
    -0.56
    <bos>
    -0.52
    šanas
    -0.47
    няет
    -0.46
     merasa
    -0.45
    nean
    -0.44
    といけない
    -0.43
     autorytatywna
    -0.43
     hjel
    -0.43
    POSITIVE LOGITS
    PRNewswire
    0.61
    EDEFAULT
    0.58
    IVEREF
    0.57
    PerformLayout
    0.53
    ளி
    0.52
     itſelf
    0.52
     onPostExecute
    0.51
    ManagedBean
    0.50
    BASEPATH
    0.49
    Према
    0.49
    Activations Density 2.128%

    No Known Activations