© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4871
    Prev
    Next
    INDEX
    Explanations

    punctuation near words like "said" and after sentences

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    "
    -2.00
    ".
    -1.66
    "?
    -1.59
    ",
    -1.58
    "-
    -1.55
    "
    -1.54
    ,"
    -1.45
    "'
    -1.44
    ."
    -1.44
    ")
    -1.44
    POSITIVE LOGITS
     “
    1.14
    ÈME
    0.58
     ‘
    0.57
    LEncoder
    0.54
     ProtoMessage
    0.52
    ADORA
    0.48
     (“
    0.48
    ereien
    0.47
     cherchés
    0.47
    ÚS
    0.46
    Activations Density 5.176%

    No Known Activations