© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6052
    Prev
    Next
    INDEX
    Explanations

    words related to broadcast media and programs.

    oai_token-act-pair · gemini-2.0-flash

    terms related to hosting or presenters

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

    host

    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
    CppMethod
    -0.74
    urably
    -0.62
    expandindo
    -0.60
     Италијани
    -0.59
    DateTimeField
    -0.58
     bershka
    -0.57
     فريبيس
    -0.56
    カンド
    -0.56
    BeginContext
    -0.55
     rospy
    -0.55
    POSITIVE LOGITS
     host
    2.31
     hosts
    2.16
     Host
    2.09
    host
    1.97
    Host
    1.96
     Hosts
    1.92
     hosting
    1.92
     HOST
    1.77
    hosts
    1.76
     hosted
    1.76
    Activations Density 2.017%

    No Known Activations