© 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. 5959
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sharp objects, especially blades

    oai_token-act-pair · gemini-2.0-flash

    tools and hardware

    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
    AsUp
    -0.69
     >=",
    -0.60
    enderror
    -0.60
    kháu
    -0.59
    Grip
    -0.57
    glEnd
    -0.55
    GOTREF
    -0.55
     handleMessage
    -0.55
     esternos
    -0.55
     '\\;'
    -0.54
    POSITIVE LOGITS
     cucchiaio
    0.52
    EndContext
    0.52
    avad
    0.52
    \{\\
    0.50
     CGSize
    0.47
    wart
    0.46
     administration
    0.46
    験
    0.46
    ERICK
    0.46
    באנגלית
    0.46
    Activations Density 5.601%

    No Known Activations