© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 835
    Prev
    Next
    INDEX
    Explanations

    words and phrases in all caps, often in a heading

    oai_token-act-pair · gemini-2.0-flash

    Random content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     CHAR
    -0.57
     MAT
    -0.57
     MED
    -0.56
     VAL
    -0.56
     STAR
    -0.56
     LOG
    -0.56
     VIR
    -0.56
     MET
    -0.55
     DEV
    -0.55
     CUR
    -0.55
    POSITIVE LOGITS
    Fordítás
    0.24
    تم
    0.22
    PyObject
    0.21
    CppCodeGen
    0.20
    freopen
    0.20
    よ
    0.19
    CMV
    0.19
    Kaieteur
    0.19
    jectures
    0.19
    QCD
    0.18
    Activations Density 3.903%

    No Known Activations