© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3442
    Prev
    Next
    INDEX
    Explanations

    words related to law and government

    oai_token-act-pair · gemini-2.0-flash

    historical/political texts

    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
    WebControls
    -0.49
    racha
    -0.45
     rospy
    -0.42
    ském
    -0.37
    DebuggerNonUser
    -0.37
    imageio
    -0.37
    aspects
    -0.37
     Serikat
    -0.36
    FormTagHelper
    -0.36
    örs
    -0.36
    POSITIVE LOGITS
    fitrión
    0.74
    featureID
    0.73
     autorytatywna
    0.73
    BeginContext
    0.70
     Normdatei
    0.66
    SourceChecksum
    0.64
     oration
    0.64
     personage
    0.63
    Geplaatst
    0.61
    TagMode
    0.60
    Activations Density 3.732%

    No Known Activations