© 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. 11915
    Prev
    Next
    INDEX
    Explanations

    German sentences and clauses dealing with writing, thinking, and knowledge

    oai_token-act-pair · gemini-2.0-flash

    multilingual texts

    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
     blunt
    -0.53
     kasarigan
    -0.51
     pluralism
    -0.50
    World
    -0.50
     empiric
    -0.48
     Administrativna
    -0.48
     extremism
    -0.48
     PARSER
    -0.48
    kli
    -0.46
     placent
    -0.46
    POSITIVE LOGITS
     cherchés
    0.49
     Adu
    0.46
     Es
    0.42
    CppCodeGen
    0.40
     Ses
    0.39
     Bil
    0.38
    umina
    0.37
     Arthur
    0.37
    Carriera
    0.37
     Res
    0.37
    Activations Density 0.066%

    No Known Activations