© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14738
    Prev
    Next
    INDEX
    Explanations

    text in a non-English language related to Facebook accounts and phone numbers

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     kasarigan
    -0.53
     ➢
    -0.49
    protoimpl
    -0.48
    bootstrapcdn
    -0.47
    醐
    -0.47
     TextAppearance
    -0.46
    zzleHttp
    -0.45
    ěř
    -0.44
    rawn
    -0.43
     YB
    -0.43
    POSITIVE LOGITS
    httphttps
    0.64
    inetti
    0.59
    ]--;
    0.58
     везе
    0.56
    ometra
    0.54
     riuscito
    0.53
    XmlAccessType
    0.52
    invokeLater
    0.52
     nécessité
    0.51
    üğü
    0.51
    Activations Density 7.081%

    No Known Activations