© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6260
    Prev
    Next
    INDEX
    Explanations

    a reviewer expressing opinions and preferences while describing their experience of watching movies, especially anime

    oai_token-act-pair · gemini-2.0-flash

    words related to watching or streaming media

    np_token-act-pair-logits · gpt-4o-mini

    watch related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ^(@)
    -1.20
     Efq
    -1.15
     Jefus
    -1.06
     myſelf
    -1.04
     itſelf
    -1.03
    __":
    -1.01
     ་་
    -1.00
    ſelf
    -1.00
     Theſe
    -0.99
     Anſ
    -0.97
    POSITIVE LOGITS
     watch
    0.68
     watched
    0.67
    Watch
    0.64
    watch
    0.58
     Watch
    0.57
     watching
    0.57
    Stream
    0.56
    stream
    0.50
     stream
    0.49
     espectadores
    0.47
    Activations Density 2.418%

    No Known Activations