© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12852
    Prev
    Next
    INDEX
    Explanations

    the word "side" and words related to it (one, other, another) and locations, or words that connote a duality, or bias.

    oai_token-act-pair · gemini-2.0-flash

    side

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     side
    -1.28
     Side
    -1.16
    Side
    -1.10
     SIDE
    -1.03
    side
    -0.93
     sides
    -0.93
     lado
    -0.92
    SIDE
    -0.89
     sided
    -0.80
     côté
    -0.79
    POSITIVE LOGITS
    Pyx
    0.60
     CURIAM
    0.56
    enumii
    0.53
     wipers
    0.48
    ksom
    0.48
    Segu
    0.46
    ALAM
    0.45
    sur
    0.45
    fjspx
    0.45
     estimés
    0.45
    Activations Density 16.235%

    No Known Activations