© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16229
    Prev
    Next
    INDEX
    Explanations

    the word "statements"

    oai_token-act-pair · gemini-2.0-flash

    statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    s
    -1.16
    a
    -1.02
    ↵↵
    -1.02
    (
    -0.94
    d
    -0.92
    e
    -0.91
    er
    -0.90
    i
    -0.89
    t
    -0.88
    r
    -0.88
    POSITIVE LOGITS
     виправивши
    1.44
     للاسماء
    1.38
     resourceCulture
    1.30
    fjspx
    1.24
    ^(@)
    1.22
     Мексичка
    1.20
    OGND
    1.18
     tartalomajánló
    1.16
    Personendaten
    1.12
     Савезне
    1.11
    Activations Density 1.715%

    No Known Activations