© 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. 3803
    Prev
    Next
    INDEX
    Explanations

    acronyms for organizations and teams

    oai_token-act-pair · gemini-2.0-flash

    organizations

    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
    bootstrapcdn
    -0.44
    inline
    -0.40
    []>
    -0.38
     
    -0.38
    φέρ
    -0.38
    f
    -0.35
    ben
    -0.35
    　（
    -0.35
    b
    -0.35
    下载附件
    -0.34
    POSITIVE LOGITS
    Vidite
    0.82
    Kaynakça
    0.76
     enacted
    0.74
    Coordonnées
    0.74
    GETHER
    0.71
     handed
    0.70
     destroyed
    0.70
     launched
    0.69
     sent
    0.69
     transferred
    0.68
    Activations Density 3.304%

    No Known Activations