© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6851
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs including inequalities and uses of "we have"

    oai_token-act-pair · gemini-2.0-flash

    academic research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     using
    -0.93
    using
    -0.80
     USING
    -0.75
     utilizing
    -0.75
     utilizzando
    -0.73
    Using
    -0.69
     Using
    -0.66
    SourceChecksum
    -0.66
     Réponses
    -0.65
     utilising
    -0.65
    POSITIVE LOGITS
     used
    2.73
     Used
    2.66
    Used
    2.58
    used
    2.48
     USED
    2.33
     usado
    1.77
    USED
    1.77
     usada
    1.66
     usados
    1.66
     utilisé
    1.57
    Activations Density 6.539%

    No Known Activations