© 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. 13353
    Prev
    Next
    INDEX
    Explanations

    words related to fictional or mythical little people and the word "shel"

    oai_token-act-pair · gemini-2.0-flash

    fief

    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
    SequentialGroup
    -1.20
     للمعارف
    -1.09
    Personendaten
    -1.04
    GraphicsUnit
    -0.98
    AndEndTag
    -0.96
    AxisAlignment
    -0.92
    MemoryWarning
    -0.91
     resourceCulture
    -0.89
     كومونز
    -0.89
    tagHelperRunner
    -0.85
    POSITIVE LOGITS
    fs
    0.79
    f
    0.79
    ff
    0.68
    fb
    0.65
    fw
    0.62
    fz
    0.62
    ft
    0.61
    fm
    0.61
    lf
    0.60
    fname
    0.58
    Activations Density 3.156%

    No Known Activations