© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6214
    Prev
    Next
    INDEX
    Explanations

    code snippets, definitions, or file paths

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     protoimpl
    -0.88
     betweenstory
    -0.87
    InitVars
    -0.76
    AddTagHelper
    -0.74
    AndEndTag
    -0.73
     Мексичка
    -0.73
    TestingModule
    -0.72
    verwijspagina
    -0.72
     MainAxisSize
    -0.72
    sidemargin
    -0.71
    POSITIVE LOGITS
    .
    1.95
    '.
    1.57
    ".
    1.53
    .
    1.49
    ’.
    1.41
    $.
    1.39
    ”.
    1.38
    ().
    1.36
    ].
    1.34
    ."
    1.34
    Activations Density 10.031%

    No Known Activations