© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9897
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and control characters appearing in how-to guides

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ViewImports
    -0.57
    SequentialGroup
    -0.55
     AssemblyVersion
    -0.51
     utafitiHapana
    -0.50
    stateProvider
    -0.50
    ophagus
    -0.49
    Jereo
    -0.49
    routeProvider
    -0.49
    Xna
    -0.48
    leby
    -0.48
    POSITIVE LOGITS
    ngdoc
    0.59
    }));
    0.55
    ↵↵
    0.54
    ValueGenerated
    0.53
     They
    0.51
     resourceCulture
    0.50
    })->
    0.49
     */;
    0.48
    <>();
    0.48
     And
    0.47
    Activations Density 0.609%

    No Known Activations