© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15275
    Prev
    Next
    INDEX
    Explanations

    arabic text

    oai_token-act-pair · gemini-2.0-flash

    أ

    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
    ſelf
    -0.96
    ^(@)
    -0.95
    ſelves
    -0.91
    neſs
    -0.85
     purpoſe
    -0.85
     Majefty
    -0.82
     Reſ
    -0.82
     Monfieur
    -0.81
    」,
    -0.80
     itſelf
    -0.79
    POSITIVE LOGITS
    לה
    0.63
    ma
    0.63
     ا
    0.61
    I
    0.59
    أ
    0.59
    ou
    0.58
    !
    0.57
     آ
    0.56
    E
    0.56
    とお
    0.55
    Activations Density 0.483%

    No Known Activations