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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10303
    Prev
    Next
    INDEX
    Explanations

    words, acronyms and numbers related to computer hardware and software

    oai_token-act-pair · gemini-2.0-flash

    Connection ports and devices

    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
     <=",
    -0.88
     autorytatywna
    -0.77
    LookAnd
    -0.77
    ImageContext
    -0.75
    mergeFrom
    -0.75
    +#+
    -0.72
    esModule
    -0.70
    titleMargin
    -0.70
     صوتيه
    -0.69
    MessageTagHelper
    -0.69
    POSITIVE LOGITS
    ps
    0.50
    المكان
    0.43
    Rè
    0.40
     منه
    0.37
    dt
    0.36
     DbContext
    0.36
    Util
    0.35
     uitzicht
    0.35
    RegisterType
    0.35
    Type
    0.34
    Activations Density 0.465%

    No Known Activations