© 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. 16263
    Prev
    Next
    INDEX
    Explanations

    the "Hol" substring within words

    oai_token-act-pair · gemini-2.0-flash

    hol

    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
     Signalez
    -0.59
    httphttps
    -0.54
    허
    -0.52
    Portale
    -0.50
    hbs
    -0.49
    ellum
    -0.48
    WindowConstants
    -0.48
    queryInterface
    -0.47
     gemeint
    -0.47
    ipal
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    TargetException
    0.60
    OGND
    0.56
     setEmail
    0.53
    makeText
    0.52
     utafitiHapana
    0.52
    Биография
    0.49
     ErrIntOverflow
    0.48
     للاسماء
    0.47
     pror
    0.47
    Activations Density 0.305%

    No Known Activations