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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15000
    Prev
    Next
    INDEX
    Explanations

    various forms of the words 'to', 'you', 'are', 'going', and 'the' in the vicinity of other keywords, especially verbs.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    mappedBy
    -0.47
     tele
    -0.44
    Clik
    -0.44
    kind
    -0.43
    십시오
    -0.43
    ریه
    -0.42
     oublié
    -0.42
    wait
    -0.42
    HasMaxLength
    -0.42
    ிறது
    -0.41
    POSITIVE LOGITS
    oa̍t
    0.81
     архивлан
    0.78
     Италијани
    0.69
     للاسماء
    0.65
    rungsseite
    0.65
    rouvez
    0.65
    ostruct
    0.65
     calendriers
    0.63
    SourceChecksum
    0.62
    writeFieldEnd
    0.62
    Activations Density 2.829%

    No Known Activations