© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4310
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly those using PHP and Javascript

    oai_token-act-pair · gemini-2.0-flash

    code snippet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     للمعارف
    -1.20
     صوتيه
    -1.04
    DeleteBehavior
    -0.93
    -0.88
     للاسماء
    -0.83
    ConstraintMaker
    -0.83
    IntoConstraints
    -0.82
    RetentionPolicy
    -0.82
    AndroidJUnit
    -0.81
    Hochspringen
    -0.81
    POSITIVE LOGITS
    Notae
    0.45
    arpa
    0.40
    фер
    0.38
     storica
    0.38
    คม
    0.37
     manier
    0.37
     catalogo
    0.36
     assisti
    0.35
     otak
    0.35
    amo
    0.35
    Activations Density 0.393%
    No Known Activations