© 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. 13138
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related text, possibly including aspects of file formats or MIME types.

    oai_token-act-pair · gemini-2.0-flash

    computer code or messaging

    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
     insuffisamment
    -0.68
    ^(@)
    -0.67
    ]]:
    -0.66
    mybatisplus
    -0.65
     Exacts
    -0.65
    uroy
    -0.64
     ModelRenderer
    -0.64
    참고
    -0.63
     useContext
    -0.61
    abetes
    -0.61
    POSITIVE LOGITS
    pleft
    0.47
    пти
    0.46
    occu
    0.45
     murales
    0.42
    pd
    0.41
    itere
    0.41
     blik
    0.41
    CAP
    0.41
     regionales
    0.40
    Dữ
    0.40
    Activations Density 0.982%

    No Known Activations