© 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. 11685
    Prev
    Next
    INDEX
    Explanations

    code snippets, possibly from different languages, that contain keywords like "module", "property", "part", "map", and "combat".

    oai_token-act-pair · gemini-2.0-flash

    say period

    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
    OGND
    -1.15
     protoimpl
    -1.12
     ProtoMessage
    -1.07
     OFDb
    -1.05
    SourceChecksum
    -1.03
    évaluateur
    -0.98
     الرياضيه
    -0.97
    "])
    -0.94
    Personendaten
    -0.93
    XmlAccessorType
    -0.92
    POSITIVE LOGITS
    .
    0.68
    di
    0.42
    !.
    0.40
     års
    0.40
    ?.
    0.39
    .$
    0.39
     darb
    0.39
     DAG
    0.37
     Prid
    0.37
     lâng
    0.37
    Activations Density 14.518%

    No Known Activations