© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3449
    Prev
    Next
    INDEX
    Explanations

    verbs related to violent events, actions related to horses, and food acquisition

    oai_token-act-pair · gemini-2.0-flash

    words related to animals

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

    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_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
     Tail
    -0.54
    ardless
    -0.48
    uteurs
    -0.46
     TAIL
    -0.46
    Tail
    -0.45
     Kara
    -0.44
    TAIL
    -0.44
     grà
    -0.43
     tail
    -0.43
    oyer
    -0.43
    POSITIVE LOGITS
     animals
    1.74
     animal
    1.60
    Animals
    1.44
     Animals
    1.41
     animale
    1.41
    animal
    1.40
    animals
    1.39
     animali
    1.33
    Animal
    1.30
     ANIMAL
    1.30
    Activations Density 1.927%

    No Known Activations