© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3644
    Prev
    Next
    INDEX
    Explanations

    multiple lettered items encased in parentheses in survey like questions

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    none
    -1.57
     none
    -1.51
    None
    -1.44
     everyone
    -1.35
     None
    -1.32
    everyone
    -1.30
     NONE
    -1.28
    anyone
    -1.25
    NONE
    -1.21
     everybody
    -1.20
    POSITIVE LOGITS
    cyklopedia
    0.57
    цезда
    0.56
    <bos>
    0.54
    piram
    0.54
    Còn
    0.53
    __*/
    0.52
    mybatisplus
    0.50
    帖最后由
    0.49
    ParallelGroup
    0.49
    ticale
    0.49
    Activations Density 1.263%

    No Known Activations