© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13786
    Prev
    Next
    INDEX
    Explanations

    words associated with political news

    oai_token-act-pair · gemini-2.0-flash

    reporting verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     CreateTagHelper
    -0.69
    EndProject
    -0.68
    TemporalType
    -0.61
     opérés
    -0.61
     Normdatei
    -0.60
    الإنجليزية
    -0.58
     дописавши
    -0.57
    Hochspringen
    -0.57
    DockStyle
    -0.55
     useStyles
    -0.52
    POSITIVE LOGITS
    ystis
    0.52
    További
    0.52
    Ĉ
    0.52
     ويكيميديا
    0.51
    rolid
    0.49
    änien
    0.48
    marle
    0.48
    naeus
    0.47
    ็บ
    0.47
     Booster
    0.47
    Activations Density 39.645%

    No Known Activations