© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5850
    Prev
    Next
    INDEX
    Explanations

    the verb "have" and its conjugated forms, but also the verbs "need", "love", "try" and the conjunction "but"

    oai_token-act-pair · gemini-2.0-flash

    have

    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
    Has
    -0.56
    ...
    -0.49
    …
    -0.48
    has
    -0.47
    open
    -0.46
    S
    -0.46
    f
    -0.46
    ne
    -0.45
    he
    -0.44
    ..
    -0.43
    POSITIVE LOGITS
     Efq
    1.29
     propOrder
    1.20
    migrationBuilder
    1.13
     Monfieur
    1.04
    hdashline
    1.04
     raiſ
    1.01
     Jefus
    1.00
     doubtnut
    1.00
     uſed
    0.98
    Билгалдахарш
    0.98
    Activations Density 1.058%

    No Known Activations