© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4255
    Prev
    Next
    INDEX
    Explanations

    German words, especially verbs, related to rules, permissions, and personal experiences

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
     ModelExpression
    -0.76
     محفوظة
    -0.60
     calendriers
    -0.60
    StoryboardSegue
    -0.59
     विश्वसनीयता
    -0.59
     للاسماء
    -0.58
    حوالہ
    -0.53
    contentLoaded
    -0.53
    šė
    -0.52
    énario
    -0.51
    POSITIVE LOGITS
     econômica
    0.50
     particulière
    0.50
    ITZ
    0.49
     volontaire
    0.48
    umpul
    0.48
     délic
    0.47
     föruts
    0.45
     doulou
    0.45
     lumineuse
    0.45
    gut
    0.45
    Activations Density 0.274%

    No Known Activations