© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9031
    Prev
    Next
    INDEX
    Explanations

    mentions of Deloitte's Fast 500 program

    oai_token-act-pair · gemini-2.0-flash

    Conferences and championships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    __*/
    -0.65
    AnchorTagHelper
    -0.63
     resourceCulture
    -0.60
     esboço
    -0.53
     مشين
    -0.51
    ंदीखरीदारी
    -0.51
    RUnlock
    -0.51
    WriteTagHelper
    -0.50
    EDEFAULT
    -0.49
    libft
    -0.48
    POSITIVE LOGITS
     Conference
    0.62
     Championship
    0.59
     Fellowship
    0.57
     CONFERENCE
    0.55
    achie
    0.54
    Conference
    0.54
     conference
    0.54
    RegressionTest
    0.53
     Hall
    0.51
     CUP
    0.50
    Activations Density 10.747%

    No Known Activations