© 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. 5654
    Prev
    Next
    INDEX
    Explanations

    advice or instructions, often related to training or patience

    oai_token-act-pair · gemini-2.0-flash

    patient

    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
     noun
    -0.54
     doPost
    -0.51
    Rujuakan
    -0.50
    >';
    -0.49
    نائ
    -0.49
    FormTagHelper
    -0.47
    ">',
    -0.47
    Географиясе
    -0.47
     newOwner
    -0.47
     demurrer
    -0.46
    POSITIVE LOGITS
     patient
    2.52
    patient
    2.11
     Patient
    2.02
    Patient
    1.98
     PATIENT
    1.83
     paciente
    1.66
    PATIENT
    1.56
     patients
    1.55
     Patients
    1.41
    Patients
    1.40
    Activations Density 3.915%

    No Known Activations