© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11914
    Prev
    Next
    INDEX
    Explanations

    words related to actions performed by more than one person or animal.

    oai_token-act-pair · gemini-2.0-flash

    dogs or drug operation

    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
     cref
    -0.69
    mybatisplus
    -0.68
     EnglishChoose
    -0.67
     "..\..\..\
    -0.65
    ⓧ
    -0.60
     displayed
    -0.59
    queryInterface
    -0.58
    writeField
    -0.57
     referenties
    -0.57
     QName
    -0.57
    POSITIVE LOGITS
    ImageContext
    0.59
    FormTagHelper
    0.44
    sume
    0.41
    localctx
    0.41
    aronder
    0.40
     lettere
    0.39
    apka
    0.38
    持つ
    0.38
     ơn
    0.38
     dator
    0.38
    Activations Density 2.338%

    No Known Activations