© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13039
    Prev
    Next
    INDEX
    Explanations

    labels or names involved in some kind of academic research such as a policy name, a math variable, or a model parameter.

    oai_token-act-pair · gemini-2.0-flash

    Code/math/algorithms/trees

    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
    AndEndTag
    -1.09
    expandindo
    -1.07
    adaptiveStyles
    -1.02
     GenerationType
    -0.95
    Portail
    -0.93
    afficheront
    -0.91
     JpaRepository
    -0.90
    InitVars
    -0.88
    ########.
    -0.85
     createSlice
    -0.84
    POSITIVE LOGITS
     Du
    0.46
     du
    0.45
     es
    0.44
     tal
    0.43
     er
    0.42
     D
    0.42
     fre
    0.42
     sar
    0.42
     True
    0.41
    Du
    0.41
    Activations Density 6.157%

    No Known Activations