© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15124
    Prev
    Next
    INDEX
    Explanations

    code documentation

    oai_token-act-pair · gemini-2.0-flash

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.66
    ########.
    -0.48
    CJK
    -0.47
     EClass
    -0.45
    readObject
    -0.44
    hibe
    -0.41
    الإنجليزية
    -0.40
    isa
    -0.40
    ukan
    -0.40
    lal
    -0.39
    POSITIVE LOGITS
     vectorielle
    0.47
     vectorielles
    0.40
     Theſe
    0.38
    GenerationType
    0.37
    othesis
    0.37
    phalt
    0.36
    rupulous
    0.35
    monials
    0.33
     provisoire
    0.33
     ویکی‌پدیا
    0.32
    Activations Density 0.306%

    No Known Activations