© 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. 8408
    Prev
    Next
    INDEX
    Explanations

    words associated with landscape and art, particularly with colorful and desolate landscapes

    oai_token-act-pair · gemini-2.0-flash

    geographical locations

    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
     terrain
    -1.02
     mountain
    -1.02
     hill
    -0.99
     landscape
    -0.97
     Landscape
    -0.96
     Forests
    -0.95
     rivers
    -0.94
     roads
    -0.94
     hills
    -0.93
     المعيارى
    -0.93
    POSITIVE LOGITS
     plain
    0.52
     portata
    0.51
    ELTS
    0.44
    ilung
    0.44
    AlterField
    0.44
    plain
    0.42
    griffen
    0.42
     verwacht
    0.42
    úcar
    0.41
    elif
    0.41
    Activations Density 1.337%

    No Known Activations