© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4974
    Prev
    Next
    INDEX
    Explanations

    words related to manufacturing or scientific instruments and their properties

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
     anlam
    -0.54
    šanai
    -0.47
     habet
    -0.47
     pauvres
    -0.47
     talle
    -0.45
     rapides
    -0.44
     positivas
    -0.44
     semula
    -0.44
     segni
    -0.43
     espirituales
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.85
     snippetHide
    0.77
    OGND
    0.77
     pinulongan
    0.77
     Normdatei
    0.71
    StoryboardSegue
    0.71
    })();
    0.69
     betweenstory
    0.67
     doInBackground
    0.66
     pips
    0.66
    Activations Density 2.612%

    No Known Activations