© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15891
    Prev
    Next
    INDEX
    Explanations

    phrases related to local SEO and business listings, and also seems to have some false positives on other kinds of business-related language.

    oai_token-act-pair · gemini-2.0-flash

    Business/Legal web pages

    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
     متعلقه
    -0.73
     '\\;'
    -0.57
     nakalista
    -0.55
     AssemblyCulture
    -0.54
    DockStyle
    -0.53
    KommentareTeilen
    -0.52
    jelen
    -0.51
    GEBURTSDATUM
    -0.51
    Tic
    -0.49
    Diweddarwch
    -0.49
    POSITIVE LOGITS
     Injury
    0.68
    новниш
    0.59
    UnknownFields
    0.56
    Injury
    0.55
     entanto
    0.55
     Wikimedijinoj
    0.55
     car
    0.53
    ***********/
    0.53
    umos
    0.52
    setPower
    0.52
    Activations Density 9.390%

    No Known Activations