© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 497
    Prev
    Next
    INDEX
    Explanations

    words relating to credit reports and scores

    oai_token-act-pair · gemini-2.0-flash

    Credit reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Réponses
    -0.68
    sidemargin
    -0.65
     дописавши
    -0.64
    Personendaten
    -0.62
    ⓧ
    -0.57
    sizeCache
    -0.55
     HasFactory
    -0.53
     الاطلاع
    -0.53
     مشين
    -0.52
    UnusedPrivate
    -0.51
    POSITIVE LOGITS
    tache
    0.60
    bibli
    0.56
    AndroidJUnit
    0.55
    INGEN
    0.54
    glTex
    0.54
    woke
    0.54
    noy
    0.53
    passphrase
    0.53
    ableness
    0.52
    pexpr
    0.52
    Activations Density 25.925%

    No Known Activations