© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10393
    Prev
    Next
    INDEX
    Explanations

    words and emojis sprinkled throughout internet articles

    oai_token-act-pair · gemini-2.0-flash

    animals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    rom
    -0.40
    Lec
    -0.38
    boleh
    -0.36
    甘
    -0.36
    Everywhere
    -0.35
     MusicBrainz
    -0.35
    Jsp
    -0.35
    Prom
    -0.35
     Fre
    -0.35
    Fre
    -0.34
    POSITIVE LOGITS
     bear
    1.33
     tiger
    1.27
     elephant
    1.23
     fox
    1.20
     Bear
    1.18
     Elephant
    1.17
     wolf
    1.15
     lion
    1.13
     leopard
    1.09
     BEAR
    1.09
    Activations Density 4.527%

    No Known Activations