© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4650
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems and accusations

    oai_token-act-pair · gemini-2.0-flash

    Past-tense action verbs

    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
    hani
    -0.35
    ())),
    -0.35
    кин
    -0.33
    ieu
    -0.32
    coba
    -0.32
    )}{(
    -0.31
    ีย
    -0.31
     ");
    -0.31
    akos
    -0.31
    לה
    -0.30
    POSITIVE LOGITS
     released
    1.58
     performed
    1.54
     conducted
    1.53
     executed
    1.51
     produced
    1.45
     delivered
    1.43
     implemented
    1.42
     obtained
    1.42
     submitted
    1.42
     played
    1.41
    Activations Density 27.762%

    No Known Activations