© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10057
    Prev
    Next
    INDEX
    Explanations

    phrases that express "difference" or contrast

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    InputBorder
    -0.94
    TagMode
    -0.86
    RectangleBorder
    -0.72
     endregion
    -0.72
     "..\..\..\
    -0.68
    ResumeLayout
    -0.67
    ſelf
    -0.66
     "..\..\
    -0.66
    IBOutlet
    -0.66
     Normdatei
    -0.66
    POSITIVE LOGITS
     but
    0.46
     same
    0.46
    曖昧さ回避
    0.44
    +#+#
    0.43
    دانشنامهٔ
    0.43
    нија
    0.43
    .
    0.41
    ])));
    0.41
     and
    0.40
     kr
    0.39
    Activations Density 1.472%

    No Known Activations