© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 731
    Prev
    Next
    INDEX
    Explanations

    phrases involving the words "need", "can", and "must"

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Roskov
    -0.68
     estekak
    -0.62
    ParallelGroup
    -0.61
     gramas
    -0.60
     rospy
    -0.60
    RunWith
    -0.58
    řev
    -0.55
     domestiques
    -0.54
    rmtree
    -0.54
    DIPSETTING
    -0.53
    POSITIVE LOGITS
    <bos>
    0.62
     be
    0.59
    TagMode
    0.54
    må
    0.52
    不必
    0.52
     needn
    0.51
     must
    0.51
    jsdelivr
    0.50
    Nationalité
    0.49
    ANDUM
    0.49
    Activations Density 1.860%

    No Known Activations