© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8715
    Prev
    Next
    INDEX
    Explanations

    content related to comics and cartooning, especially comic strips

    oai_token-act-pair · gemini-2.0-flash

    comic strips or panels

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

    Comic strips

    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
    MigrationBuilder
    -0.79
    StoryboardSegue
    -0.71
    mybatisplus
    -0.67
    IntoConstraints
    -0.64
     protoimpl
    -0.61
     metav
    -0.60
    tvguidetime
    -0.59
    aarrggbb
    -0.58
    Obrázky
    -0.57
     صوتيه
    -0.57
    POSITIVE LOGITS
     panel
    0.63
     strip
    0.60
    panel
    0.59
    Dens
    0.58
    AttributeSet
    0.56
     strips
    0.52
     panels
    0.51
    usercontent
    0.50
    AxisSize
    0.49
     Panel
    0.49
    Activations Density 1.413%

    No Known Activations