© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12914
    Prev
    Next
    INDEX
    Explanations

    references to comparisons between, and different types of, multiple items, be they people, places, or things

    oai_token-act-pair · gemini-2.0-flash

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Others
    -0.50
    PreExecute
    -0.49
    Others
    -0.47
     Pind
    -0.47
    PyExc
    -0.47
     Matka
    -0.46
     StringTokenizer
    -0.45
    曖昧さ回避
    -0.45
     columbia
    -0.45
    ᅠ
    -0.44
    POSITIVE LOGITS
     مشين
    0.79
    Архівовано
    0.69
    scriptcase
    0.68
    OwnProperty
    0.67
    fjspx
    0.63
     виправивши
    0.62
    łaszcza
    0.62
    DIPSETTING
    0.60
    قایناقلار
    0.60
    AndEndTag
    0.58
    Activations Density 5.381%

    No Known Activations