© 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. 9848
    Prev
    Next
    INDEX
    Explanations

    text related to anime and recommendations.

    oai_token-act-pair · gemini-2.0-flash

    technical or specific terminology

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

    anime and manga

    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
    MLLoader
    -0.57
     SafeMath
    -0.46
    SizeF
    -0.45
     Dax
    -0.43
     estimés
    -0.42
    hud
    -0.41
    wied
    -0.41
     Apparatus
    -0.40
    angg
    -0.40
     embry
    -0.40
    POSITIVE LOGITS
     ProtoMessage
    0.72
     betweenstory
    0.71
    expandindo
    0.63
    InSection
    0.62
    Personensuche
    0.61
    BagLayout
    0.60
    Atsauces
    0.60
     surla
    0.57
    GraphicsUnit
    0.57
    mendation
    0.56
    Activations Density 1.215%

    No Known Activations