© 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. 8405
    Prev
    Next
    INDEX
    Explanations

    words or numbers related to business and geography

    oai_token-act-pair · gemini-2.0-flash

    Company locations/facilities

    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
    IUrlHelper
    -0.66
    SourceChecksum
    -0.65
    ItemBackground
    -0.61
    ConstraintMaker
    -0.57
    onAttach
    -0.56
     plant
    -0.56
    sidemargin
    -0.56
    GraphicsUnit
    -0.55
     InputDecoration
    -0.52
    Jeografia
    -0.52
    POSITIVE LOGITS
     épic
    0.55
     legno
    0.53
     Hunters
    0.51
    ungk
    0.51
     Woodbridge
    0.50
    omers
    0.49
     commissioners
    0.49
    AndEndTag
    0.49
    therlands
    0.48
    Naissance
    0.47
    Activations Density 3.507%

    No Known Activations