© 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. 4266
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of computers or systems

    oai_token-act-pair · gemini-2.0-flash

    video content

    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
     chi̍t
    -0.77
    AnchorStyles
    -0.73
     Jefus
    -0.65
     Efq
    -0.64
     uſ
    -0.64
     paſſ
    -0.63
    Scénario
    -0.61
     Chriftian
    -0.61
     poffible
    -0.61
     Monfieur
    -0.61
    POSITIVE LOGITS
     CanadaChoose
    0.57
     video
    0.56
     vídeo
    0.51
     Video
    0.49
    Video
    0.48
    video
    0.46
    /***/
    0.45
    ógicas
    0.44
    Vídeo
    0.43
     VIDEO
    0.42
    Activations Density 2.533%

    No Known Activations