© 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. 8504
    Prev
    Next
    INDEX
    Explanations

    the upper-case letter "F" in various contexts including medical and political ones

    oai_token-act-pair · gemini-2.0-flash

    F

    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
     propOrder
    -0.82
    #
    -0.75
    Personensuche
    -0.74
    AndEndTag
    -0.74
     defStyle
    -0.72
    Espèce
    -0.70
    resave
    -0.69
    enumii
    -0.69
    HandlerContext
    -0.69
     kasarigan
    -0.69
    POSITIVE LOGITS
    urlpatterns
    0.53
    ICES
    0.52
    ICHE
    0.47
    IDES
    0.46
    IED
    0.46
    ller
    0.44
    lides
    0.44
    Попис
    0.43
    ОД
    0.42
    iela
    0.42
    Activations Density 4.771%

    No Known Activations