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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4149
    Prev
    Next
    INDEX
    Explanations

    tokens like "for" and "the" within sentences referring to movies

    oai_token-act-pair · gemini-2.0-flash

    motion picture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nahilalakip
    -0.83
    +#+
    -0.82
     cherchés
    -0.76
    LookAnd
    -0.74
     كومونز
    -0.73
     AssemblyProduct
    -0.73
     transfieras
    -0.73
    IUrlHelper
    -0.72
    省市镇
    -0.72
     Efq
    -0.71
    POSITIVE LOGITS
     picture
    1.34
     motion
    1.31
     Motion
    1.16
     Picture
    1.12
    picture
    1.10
    motion
    1.09
    Picture
    1.08
    Motion
    1.08
     PICTURE
    1.04
     MOTION
    0.97
    Activations Density 3.482%

    No Known Activations