© 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. 13854
    Prev
    Next
    INDEX
    Explanations

    text that is about living or staying somewhere

    oai_token-act-pair · gemini-2.0-flash

    residence/living

    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
     resident
    -2.55
     Residents
    -2.41
     Resident
    -2.30
    Resident
    -2.30
    Residents
    -2.27
     residents
    -2.23
    resident
    -2.17
    residents
    -2.05
     inhabitant
    -1.80
     inhabitants
    -1.73
    POSITIVE LOGITS
     tulang
    0.44
     culturali
    0.41
     Ау
    0.41
    বি
    0.40
     automatiques
    0.40
     ángeles
    0.39
    ni
    0.39
    影
    0.39
     pantallas
    0.39
    厘
    0.38
    Activations Density 1.611%

    No Known Activations