© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15647
    Prev
    Next
    INDEX
    Explanations

    general terms indicating difficulty, problems, and challenges.

    oai_token-act-pair · gemini-2.0-flash

    Technical problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    出版年
    -0.82
     فريبيس
    -0.79
    XmlAccessType
    -0.76
    RenderAtEndOf
    -0.71
    حياته
    -0.71
    évaluateur
    -0.71
     متعلقه
    -0.69
    AndEndTag
    -0.68
    HostException
    -0.68
     consultato
    -0.66
    POSITIVE LOGITS
    Humble
    0.47
    发表于
    0.42
    rophi
    0.42
    inematic
    0.41
    InputModule
    0.40
    umo
    0.40
    Länge
    0.39
    aust
    0.39
    Maße
    0.39
    LLocation
    0.39
    Activations Density 5.504%

    No Known Activations