© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8631
    Prev
    Next
    INDEX
    Explanations

    words and phrases used as evidence in an argument

    oai_token-act-pair · gemini-2.0-flash

    justification and rationale

    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
     reason
    -1.52
     cause
    -1.47
    cause
    -1.35
     caufe
    -1.32
     Cause
    -1.32
    Cause
    -1.27
     reafon
    -1.25
     cauſe
    -1.24
    reason
    -1.23
     CAUSE
    -1.21
    POSITIVE LOGITS
    راس
    0.49
     Chwiliwch
    0.49
    pé
    0.48
    STIC
    0.46
    (".");
    0.46
     PyTuple
    0.45
     gr
    0.44
    PORARY
    0.43
    CppMethod
    0.42
    ReusableCell
    0.42
    Activations Density 2.925%

    No Known Activations