© 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. 14478
    Prev
    Next
    INDEX
    Explanations

    words that are frequently used in historical texts

    oai_token-act-pair · gemini-2.0-flash

    text excerpts

    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
    WEBPACK
    -0.55
     snippetHide
    -0.54
    -------------</
    -0.50
    harusnya
    -0.48
    onente
    -0.47
     Dernière
    -0.46
    nasional
    -0.45
    })();
    -0.45
     MonoBehaviour
    -0.45
    Brainz
    -0.45
    POSITIVE LOGITS
    はじめに
    0.68
    atguigu
    0.58
    Décès
    0.56
    WebKit
    0.55
    testify
    0.53
     مُعرِّف
    0.53
    ecap
    0.52
    FieldDescriptor
    0.51
     chng
    0.51
    δρ
    0.51
    Activations Density 6.913%

    No Known Activations