© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10593
    Prev
    Next
    INDEX
    Explanations

    years represented as "200X"

    oai_token-act-pair · gemini-2.0-flash

    0

    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
     v
    -0.44
     V
    -0.44
     G
    -0.37
     F
    -0.33
     po
    -0.33
     I
    -0.32
     ne
    -0.31
     sí
    -0.31
     na
    -0.30
     si
    -0.29
    POSITIVE LOGITS
     propOrder
    0.92
     AssemblyCulture
    0.91
     للمعارف
    0.90
    InputBorder
    0.85
    دانشنامهٔ
    0.84
    PropertyGroup
    0.82
     nakalista
    0.82
    +#+#
    0.81
    verwijspagina
    0.80
     tartalomajánló
    0.80
    Activations Density 1.739%

    No Known Activations