© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10987
    Prev
    Next
    INDEX
    Explanations

    the word "So"

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    itecture
    -0.59
    tanooga
    -0.59
    thasone
    -0.59
    onation
    -0.58
    setIsLoading
    -0.56
    icina
    -0.56
    }*/
    -0.55
    leuth
    -0.54
    horizontalLayout
    -0.54
    pseud
    -0.53
    POSITIVE LOGITS
    AutoScaleMode
    0.47
     Walling
    0.47
    ple
    0.46
    PENDING
    0.45
    grade
    0.42
     Mystic
    0.42
     armée
    0.41
     généraux
    0.41
     Moo
    0.41
     pescoço
    0.41
    Activations Density 1.042%

    No Known Activations