© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14079
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and specifications, especially for products.

    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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    RenderAtEndOf
    -0.88
    RectangleBorder
    -0.85
    WriteBarrier
    -0.81
     BoxFit
    -0.81
     HasFactory
    -0.77
     AttributeSet
    -0.77
    ProgressHUD
    -0.75
     متعلقه
    -0.75
    
    -0.74
     ProtoMessage
    -0.73
    POSITIVE LOGITS
    VideoCapture
    0.42
     ex
    0.41
    をかけて
    0.39
     centrifugal
    0.37
     map
    0.36
     mek
    0.36
     BIC
    0.35
     Gun
    0.35
    วัส
    0.35
     Orte
    0.34
    Activations Density 1.148%

    No Known Activations