© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16201
    Prev
    Next
    INDEX
    Explanations

    strings of words that may be from low quality machine translation

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    transQ
    -0.78
    GEBURTSDATUM
    -0.69
     snippetHide
    -0.68
    ChildScrollView
    -0.67
    MessageTagHelper
    -0.66
    __*/
    -0.64
    ]-->
    -0.64
     CreateTagHelper
    -0.63
    IndentedString
    -0.63
    styleType
    -0.62
    POSITIVE LOGITS
    มาะ
    0.47
    レル
    0.47
     kiin
    0.44
    جهة
    0.43
     fornic
    0.43
     faith
    0.42
     Combien
    0.42
    NewGuid
    0.42
     Sask
    0.41
    elum
    0.41
    Activations Density 1.213%

    No Known Activations