© 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. 102
    Prev
    Next
    INDEX
    Explanations

    politically charged words or phrases, particularly those used in criticisms or accusations

    oai_token-act-pair · gemini-2.0-flash

    Negative political commentary

    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
    verwijspagina
    -0.91
     InputDecoration
    -0.61
     magasiner
    -0.60
     समीक्षक
    -0.60
    OGND
    -0.60
     AssemblyCulture
    -0.59
     viewDidLoad
    -0.57
    ParallelGroup
    -0.56
    POSURE
    -0.54
     MotionEvent
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.55
    tagHelper
    0.52
     Theſe
    0.50
    rash
    0.50
    BeginContext
    0.50
    newArrayList
    0.50
    assertArray
    0.49
    EndContext
    0.48
     ejus
    0.48
    reh
    0.47
    Activations Density 11.593%

    No Known Activations