© 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. 12674
    Prev
    Next
    INDEX
    Explanations

    the letters "wh"

    oai_token-act-pair · gemini-2.0-flash

    Mentions "j(wh)"

    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
    Autoritní
    -0.67
    WillAppear
    -0.60
    )))));
    -0.59
    AddTagHelper
    -0.59
    DebuggerNonUser
    -0.59
    WithIOException
    -0.57
    VIAF
    -0.57
    gwt
    -0.56
     متعلقه
    -0.56
    economia
    -0.55
    POSITIVE LOGITS
    URLException
    0.53
     iconFacebook
    0.49
    iner
    0.48
     الدولى
    0.46
     tatou
    0.45
    iners
    0.43
    tvguidetime
    0.43
    isable
    0.41
    ímite
    0.40
    ofern
    0.40
    Activations Density 0.646%

    No Known Activations