© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7774
    Prev
    Next
    INDEX
    Explanations

    the word "able", often in the context of "able to"

    oai_token-act-pair · gemini-2.0-flash

    able

    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
     définiti
    -0.77
     auroit
    -0.72
     plufieurs
    -0.72
     automatiques
    -0.70
    цездатний
    -0.69
     feroit
    -0.68
     mourut
    -0.68
     étoit
    -0.67
     Diſ
    -0.66
     تضيفلها
    -0.66
    POSITIVE LOGITS
    the
    0.59
    d
    0.58
     the
    0.55
     win
    0.52
     cater
    0.51
     reckon
    0.50
    t
    0.47
     wonder
    0.47
    be
    0.46
     hang
    0.46
    Activations Density 1.905%

    No Known Activations