© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6937
    Prev
    Next
    INDEX
    Explanations

    text related to contacting someone

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

    np_token-act-pair-logits · gpt-4o-mini

    phone calls

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     hanging
    -1.10
     hang
    -1.09
     hangs
    -1.08
    Hanging
    -1.05
     hung
    -1.03
    hanging
    -1.03
     Hanging
    -1.01
    Hang
    -0.93
    hang
    -0.89
     HANG
    -0.88
    POSITIVE LOGITS
    argout
    0.65
    RectangleBorder
    0.65
    tagHelperRunner
    0.57
     оригіналу
    0.54
     called
    0.51
    pexpr
    0.51
    classnames
    0.51
    AddTagHelper
    0.50
     createContext
    0.49
     invokingState
    0.49
    Activations Density 0.668%

    No Known Activations