© 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. 15120
    Prev
    Next
    INDEX
    Explanations

    code syntax

    oai_token-act-pair · gemini-2.0-flash

    Code and programming

    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
     I
    -1.31
     
    -1.27
     O
    -1.19
     i
    -1.16
     (
    -1.14
     d
    -1.12
     de
    -1.10
     B
    -1.09
     "
    -1.08
     et
    -1.08
    POSITIVE LOGITS
     itſelf
    3.22
     myſelf
    3.02
     Monfieur
    2.88
     Efq
    2.70
     Majefty
    2.70
     pleaſure
    2.69
     Reſ
    2.64
     Jefus
    2.61
     Diſ
    2.56
     raiſ
    2.55
    Activations Density 37.380%

    No Known Activations