© 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. 2612
    Prev
    Next
    INDEX
    Explanations

    locations and the process of obtaining something

    oai_token-act-pair · gemini-2.0-flash

    "ob" words

    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
     get
    -1.61
    get
    -1.55
     Get
    -1.53
    Get
    -1.48
     getting
    -1.46
     gets
    -1.45
     Getting
    -1.41
     gotten
    -1.41
     got
    -1.37
     Gets
    -1.34
    POSITIVE LOGITS
     ob
    1.20
     Ob
    0.98
     OB
    0.97
    ob
    0.90
    Ob
    0.82
    OB
    0.76
     OBS
    0.58
     Obs
    0.58
    obb
    0.58
     obs
    0.55
    Activations Density 3.341%

    No Known Activations