© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1884
    Prev
    Next
    INDEX
    Explanations

    text from internet chat rooms

    oai_token-act-pair · gemini-2.0-flash

    French technical text

    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
    DDG
    -0.45
     joaat
    -0.45
    ственной
    -0.44
     N
    -0.43
    N
    -0.42
     gyhoeddwyd
    -0.41
    发表于
    -0.41
    n
    -0.40
    Н
    -0.40
    thon
    -0.39
    POSITIVE LOGITS
    ]")]
    0.71
    findpost
    0.68
    providedIn
    0.66
    TagMode
    0.66
    Portail
    0.65
    endphp
    0.64
    ConstraintMaker
    0.64
     ControllerBase
    0.62
    abetes
    0.60
    CodedInputStream
    0.60
    Activations Density 0.822%

    No Known Activations