© 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. 6980
    Prev
    Next
    INDEX
    Explanations

    geographical locations, especially mountains and hills

    oai_token-act-pair · gemini-2.0-flash

    mountains and geography

    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
    expandindo
    -0.79
    ThroughAttribute
    -0.59
    IContainer
    -0.58
     <=",
    -0.56
     vPvB
    -0.52
     smart
    -0.51
    realtime
    -0.51
     nargin
    -0.50
     inz
    -0.50
    inaldi
    -0.50
    POSITIVE LOGITS
    الإنجليزية
    0.56
    adaptiveStyles
    0.54
    makeConstraints
    0.53
    SQLiteDatabase
    0.48
     Gras
    0.48
    ArrowToggle
    0.48
    asilkan
    0.47
    WireFormat
    0.46
    anat
    0.45
    GRASS
    0.45
    Activations Density 5.017%

    No Known Activations