© 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. 8373
    Prev
    Next
    INDEX
    Explanations

    sentences written in German containing modal verbs

    oai_token-act-pair · gemini-2.0-flash

    German language verbs and terms

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

    Non-English language

    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
    featureID
    -0.61
    atshirt
    -0.58
     Paglinawan
    -0.57
    tvguidetime
    -0.56
    BagConstraints
    -0.55
    AnchorStyles
    -0.54
    InitStruct
    -0.53
    AxisAlignment
    -0.52
     krijgen
    -0.52
     Ako
    -0.52
    POSITIVE LOGITS
    VersionUID
    0.54
     dem
    0.52
     j
    0.50
    WillAppear
    0.48
     ži
    0.47
     Dem
    0.47
    žin
    0.47
    Wikis
    0.46
     dir
    0.46
    mir
    0.46
    Activations Density 0.225%

    No Known Activations