© 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. 302
    Prev
    Next
    INDEX
    Explanations

    references to videos and video creation

    oai_token-act-pair · gemini-2.0-flash

    say "video"

    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
     video
    -2.81
     Video
    -2.77
    Video
    -2.67
    video
    -2.59
     videos
    -2.55
     VIDEO
    -2.47
     Videos
    -2.41
     vidéo
    -2.28
    Videos
    -2.27
    VIDEO
    -2.25
    POSITIVE LOGITS
    ErrUnexpectedEOF
    0.51
     cervello
    0.51
    XmlAccessType
    0.50
    שרה
    0.49
    tinyos
    0.48
    AsUp
    0.47
     gefeiert
    0.47
    Unmount
    0.47
    )++;
    0.47
    curkan
    0.46
    Activations Density 1.081%

    No Known Activations