© 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. 13957
    Prev
    Next
    INDEX
    Explanations

    a variety of common words and phrases, with no clear unifying concept.

    oai_token-act-pair · gemini-2.0-flash

    out

    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
    <bos>
    -0.98
    msgSender
    -0.79
    XmlEnum
    -0.75
    umbersome
    -0.71
    citep
    -0.67
    erapeu
    -0.66
    liothèque
    -0.63
    closedir
    -0.62
     pstmt
    -0.62
     Мексичка
    -0.60
    POSITIVE LOGITS
     تانيه
    0.51
    EndInit
    0.43
     noth
    0.34
    Skocz
    0.32
    ssf
    0.31
     stric
    0.31
    VersionUID
    0.31
     sufficiency
    0.30
     Circuit
    0.29
     lak
    0.29
    Activations Density 10.634%

    No Known Activations