© 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. 8772
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to experimental research and technology

    oai_token-act-pair · gemini-2.0-flash

    screen

    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
     screen
    -2.92
     Screen
    -2.86
     screens
    -2.83
     SCREEN
    -2.83
    Screen
    -2.77
    screen
    -2.72
     Screens
    -2.69
     screening
    -2.59
     Screening
    -2.58
    SCREEN
    -2.55
    POSITIVE LOGITS
    faits
    0.47
    addGap
    0.47
     rRNA
    0.47
    وفة
    0.47
     hObject
    0.46
    nsf
    0.46
     Wob
    0.45
    idopsis
    0.45
     onCancelled
    0.44
    الدراسه
    0.44
    Activations Density 1.758%

    No Known Activations