© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13270
    Prev
    Next
    INDEX
    Explanations

    the word "stable" and related words such as "stabilizing" and "destabilize"

    oai_token-act-pair · gemini-2.0-flash

    stable

    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
     idéia
    -0.69
     NavController
    -0.69
     …
    -0.64
    addPreferredGap
    -0.63
     David
    -0.62
    Hmmmm
    -0.61
    CONTENTS
    -0.60
     den
    -0.60
    Ummm
    -0.59
     informée
    -0.59
    POSITIVE LOGITS
     Jefus
    1.12
     purpoſe
    1.07
     poffe
    1.06
     Majefty
    1.06
     Shakspeare
    1.03
     ſche
    1.02
     fubject
    1.01
     itſelf
    0.98
     houſe
    0.98
     pleaſure
    0.96
    Activations Density 1.894%

    No Known Activations