© 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. 6699
    Prev
    Next
    INDEX
    Explanations

    URLs, internet addresses, and formatted emails

    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_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
     three
    -0.65
    脚注の使い方
    -0.54
    ایق
    -0.46
     nine
    -0.44
     nargin
    -0.44
    abetes
    -0.44
    ֹת
    -0.43
     Efq
    -0.43
    Herzliche
    -0.43
     Вода
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.70
    setViewportView
    0.68
    SequentialGroup
    0.64
     ModelExpression
    0.62
    PerformLayout
    0.62
    Parcelize
    0.61
    CodedInputStream
    0.60
    listFiles
    0.59
     SEDS
    0.58
    mybatisplus
    0.57
    Activations Density 17.469%

    No Known Activations