© 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. 8494
    Prev
    Next
    INDEX
    Explanations

    capitalized location names.

    oai_token-act-pair · gemini-2.0-flash

    places/locations

    np_max-act-logits · gemini-2.0-flash

    place adjectives

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Florida
    -1.39
     Texas
    -1.35
     Arizona
    -1.31
     Ohio
    -1.30
     Louisiana
    -1.27
     Colorado
    -1.26
     California
    -1.25
     Oregon
    -1.24
     Wisconsin
    -1.24
     Washington
    -1.24
    POSITIVE LOGITS
    TagMode
    0.60
     Benth
    0.55
     poética
    0.49
     ***!
    0.48
    庁
    0.47
    ワイイ
    0.47
     Políticas
    0.46
     Parad
    0.45
    minton
    0.45
    OrNil
    0.45
    Activations Density 7.405%

    No Known Activations