© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9323
    Prev
    Next
    INDEX
    Explanations

    words related to problems and their solutions

    oai_token-act-pair · gemini-2.0-flash

    solution

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    zuführen
    -0.57
    adaptiveStyles
    -0.55
    toMatchSnapshot
    -0.49
    plona
    -0.48
     umo
    -0.47
     breeches
    -0.46
     SIMBAD
    -0.46
     mantel
    -0.46
    shields
    -0.45
     internetowa
    -0.45
    POSITIVE LOGITS
     defaultstate
    0.73
    SharedDtor
    0.64
    complexContent
    0.62
    المناصب
    0.57
    verifyException
    0.56
     gyhoeddwyd
    0.56
    Carriera
    0.54
     beginnetje
    0.53
    Aholisi
    0.53
    GEBURTSDATUM
    0.53
    Activations Density 10.506%

    No Known Activations