© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 78
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    oai_token-act-pair · gemini-2.0-flash

    math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     litté
    -0.47
     assurent
    -0.47
     समीक्षाएं
    -0.44
     connexes
    -0.42
     finns
    -0.40
    $\#
    -0.40
    $=\
    -0.40
     habet
    -0.40
     soient
    -0.40
    ).(
    -0.40
    POSITIVE LOGITS
    D
    0.68
    L
    0.66
    V
    0.65
    k
    0.65
     CGPA
    0.65
     D
    0.64
    B
    0.64
    K
    0.63
     VDC
    0.63
    S
    0.63
    Activations Density 6.890%

    No Known Activations