© 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. 6760
    Prev
    Next
    INDEX
    Explanations

    a variety of words possibly related to personal pronouns, personal experiences, royalty, or locations.

    oai_token-act-pair · gemini-2.0-flash

    I

    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
     wonder
    -0.62
     BoxDecoration
    -0.57
    WriteTagHelper
    -0.54
    IntoConstraints
    -0.53
    WEBPACK
    -0.53
    +#+
    -0.52
    RequiresApi
    -0.49
    ]^{-
    -0.49
    TargetApi
    -0.49
     AssemblyVersion
    -0.49
    POSITIVE LOGITS
    
    0.59
     gyhoeddwyd
    0.59
     Roskov
    0.57
     Serve
    0.57
    MigrationBuilder
    0.54
     Ause
    0.53
     okuyayım
    0.53
    іга
    0.50
     geox
    0.50
     Operate
    0.49
    Activations Density 4.019%

    No Known Activations