© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2196
    Prev
    Next
    INDEX
    Explanations

    words relating to bones, medicine, and research.

    oai_token-act-pair · gemini-2.0-flash

    words related to bones and skeletal structures

    np_token-act-pair-logits · gpt-4o-mini

    bones

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    DebuggerNonUser
    -0.56
    ChildScrollView
    -0.52
    InjectAttribute
    -0.49
    NgModule
    -0.49
    __":
    -0.49
    endregion
    -0.46
    enumii
    -0.44
    Бахар
    -0.44
     élections
    -0.42
     sorti
    -0.41
    POSITIVE LOGITS
     bones
    0.88
     bone
    0.84
    Bone
    0.77
     skeletal
    0.76
     skeleton
    0.76
     Bone
    0.76
    bone
    0.76
     Bones
    0.75
    Bones
    0.75
     skull
    0.74
    Activations Density 2.954%

    No Known Activations