© 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. 3948
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to evidence or support of claims, often in written documents or reports.

    oai_token-act-pair · gemini-2.0-flash

    little

    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
    SharedCtor
    -0.76
     NSCoder
    -0.75
    
    -0.66
    enumi
    -0.63
     Saltar
    -0.59
    sizeCache
    -0.57
     yetu
    -0.56
     lenker
    -0.56
    RTGC
    -0.56
    inWeight
    -0.55
    POSITIVE LOGITS
     little
    3.39
    little
    3.11
    Little
    2.58
     LITTLE
    2.42
     Little
    2.31
    LITTLE
    1.98
     lil
    1.57
     litt
    1.41
     pouco
    1.38
     poco
    1.34
    Activations Density 19.802%

    No Known Activations