© 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. 4055
    Prev
    Next
    INDEX
    Explanations

    descriptions of a user modifying an object using tools or materials

    oai_token-act-pair · gemini-2.0-flash

    use

    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
    WriteBarrier
    -0.65
    DebuggerNonUser
    -0.58
    ChildScrollView
    -0.57
    kann
    -0.55
    lodash
    -0.47
    GMENT
    -0.46
    glue
    -0.46
    mannian
    -0.46
     Glue
    -0.45
     چسب
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.94
    ViewImports
    0.88
     Италијани
    0.84
    ValueStyle
    0.69
    oredCriteria
    0.62
    Bibliograf
    0.59
    ArrowToggle
    0.58
     مرئيه
    0.56
    ContentAsync
    0.53
    Autoritní
    0.53
    Activations Density 3.857%

    No Known Activations