© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6932
    Prev
    Next
    INDEX
    Explanations

    a mix of pronouns ("you", "I", "she"), auxiliary verbs ("are", "is", "has", "be"), location words ("Australia", "China", "USA"), and scientific research terms ("study", "field")

    oai_token-act-pair · gemini-2.0-flash

    Face

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ItemLayout
    -0.55
    rawDesc
    -0.47
    ಂದು
    -0.45
    picasso
    -0.45
    RunAsync
    -0.44
    petito
    -0.43
    <>
    -0.43
    delwed
    -0.43
    principalColumn
    -0.43
    offsetof
    -0.43
    POSITIVE LOGITS
     face
    3.08
     faces
    2.72
    face
    2.66
    Face
    2.59
     faced
    2.59
     facing
    2.58
     Face
    2.56
    faced
    2.34
     Facing
    2.33
     FACE
    2.27
    Activations Density 5.798%

    No Known Activations