© 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. 3
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss high-level complex issues or concepts, especially in a positive or negative light.

    oai_token-act-pair · 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
    stdc
    -0.66
    FontStyle
    -0.57
     continúas
    -0.49
    saraba
    -0.49
     AssemblyProduct
    -0.49
    TabIndex
    -0.48
    ApiModelProperty
    -0.47
    orianCalendar
    -0.47
    ]-->
    -0.46
    localPosition
    -0.44
    POSITIVE LOGITS
     uſed
    0.67
     raiſ
    0.67
    ้อมูล
    0.65
     houſe
    0.65
     uſe
    0.64
     ſever
    0.62
     juſ
    0.61
     itſelf
    0.61
     reaſon
    0.61
    UnknownFields
    0.61
    Activations Density 9.255%

    No Known Activations