© 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. 14829
    Prev
    Next
    INDEX
    Explanations

    code snippets or coding language

    oai_token-act-pair · gemini-2.0-flash

    structured data references or links

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

    Code snippets

    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
    Portale
    -0.60
    ReusableCell
    -0.56
     defaultstate
    -0.50
    بوابة
    -0.49
    SourceChecksum
    -0.49
    SafeMath
    -0.47
    +#+#
    -0.47
    StoryboardSegue
    -0.46
     AttributeSet
    -0.45
     kaynağından
    -0.44
    POSITIVE LOGITS
     bloom
    0.59
    MENAFN
    0.57
    SizeF
    0.54
    IVEREF
    0.54
     linkovi
    0.54
     walk
    0.53
     Biôgrafia
    0.51
    ParseTree
    0.51
     stretch
    0.50
     allergen
    0.50
    Activations Density 1.308%

    No Known Activations