© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4197
    Prev
    Next
    INDEX
    Explanations

    something in German; it's hard to say what specifically

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     zra
    -0.47
     st
    -0.43
    mal
    -0.41
    eadilan
    -0.40
     alle
    -0.40
     mal
    -0.40
     proofs
    -0.38
     tissus
    -0.38
     genética
    -0.37
     propres
    -0.36
    POSITIVE LOGITS
    GEBURTSDATUM
    0.84
     invokingState
    0.81
    Personensuche
    0.79
    TypedDataSet
    0.75
    InputBorder
    0.69
    DockStyle
    0.67
    OfMonth
    0.66
     crdi
    0.66
    setVerticalGroup
    0.65
    ModelSerializer
    0.64
    Activations Density 0.502%

    No Known Activations