© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3926
    Prev
    Next
    INDEX
    Explanations

    a variety of German modal verbs and auxiliary verbs (Kann, hätte) used to express possibility, ability, or obligation

    oai_token-act-pair · gemini-2.0-flash

    ätte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     afin
    -0.44
     because
    -0.43
     Band
    -0.43
     Ch
    -0.42
     Cha
    -0.42
    Med
    -0.42
    ThroughAttribute
    -0.42
     Cup
    -0.40
     speaking
    -0.40
     Cu
    -0.40
    POSITIVE LOGITS
     Normdatei
    0.85
    tagHelperRunner
    0.78
     виправивши
    0.77
    الإنجليزية
    0.77
     zelve
    0.76
    MemoryWarning
    0.75
    帖最后由
    0.75
     EnglishChoose
    0.74
     avoient
    0.74
     ainfi
    0.74
    Activations Density 0.090%

    No Known Activations