© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 5909
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and measurement values

    oai_token-act-pair · gemini-2.0-flash

    Scientific experimental data

    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
     itſelf
    -1.17
     ―――――
    -1.11
     myſelf
    -1.07
    tvguidetime
    -1.05
    ^(@)
    -1.05
     ་་
    -1.02
    >\<^
    -1.00
    CppMethod
    -0.98
     iſt
    -0.98
     ẞ
    -0.98
    POSITIVE LOGITS
     ,
    2.16
     .
    1.63
     )
    1.41
     ;
    1.34
     ).
    1.29
     ),
    1.26
     );
    1.20
     ,
    1.09
     !
    1.07
     ،
    1.05
    Activations Density 6.074%

    No Known Activations