© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12877
    Prev
    Next
    INDEX
    Explanations

    German language, specifically constructions with modal verbs such as "können", "hätte", "sollen" and related grammar.

    oai_token-act-pair · gemini-2.0-flash

    Oxidation

    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
     AssemblyCulture
    -0.58
    AutoScaleMode
    -0.57
    бият
    -0.55
    GraphicsUnit
    -0.54
    styleType
    -0.54
     nahilalakip
    -0.54
    AddTagHelper
    -0.51
     '{@
    -0.51
     åt
    -0.49
     graphiques
    -0.47
    POSITIVE LOGITS
     am
    0.85
     oxidizing
    0.79
     oxidation
    0.79
     oxid
    0.76
     oxidative
    0.73
     redox
    0.73
     Oxid
    0.73
     oxidized
    0.72
    oxid
    0.69
    Oxid
    0.62
    Activations Density 0.130%

    No Known Activations