© 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. 16101
    Prev
    Next
    INDEX
    Explanations

    uses of the word 'term' and other words describing language or ranking

    oai_token-act-pair · 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
    Rüyada
    -0.52
    <bos>
    -0.51
    __":
    -0.50
    onViewCreated
    -0.50
    الحياه
    -0.49
    OCCURRED
    -0.48
    DebuggerNonUser
    -0.48
    UIControlState
    -0.47
     gynnwys
    -0.47
    LikeLike
    -0.47
    POSITIVE LOGITS
    +#+#
    0.72
     HasFactory
    0.63
     يتيمه
    0.59
     autorytatywna
    0.59
    InstrumentedTest
    0.59
     '\\;'
    0.58
     estimés
    0.57
    ✨:
    0.55
    出版年
    0.54
    Ӕ
    0.53
    Activations Density 7.113%

    No Known Activations