© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3438
    Prev
    Next
    INDEX
    Explanations

    mentions of the social media platform Twitter

    oai_token-act-pair · gemini-2.0-flash

    Twitter

    np_max-act · gemini-2.0-flash

    Twitter

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AssemblyTitle
    -0.63
    PostExecute
    -0.60
    AsStream
    -0.59
     Poehler
    -0.58
    cipy
    -0.56
     list
    -0.56
     side
    -0.55
    esgue
    -0.55
    ControllerAdvice
    -0.53
     ModelExpression
    -0.52
    POSITIVE LOGITS
    OGND
    0.82
    parsedMessage
    0.78
    ьаж
    0.68
     {}),
    0.67
    "]).
    0.65
     resourceCulture
    0.65
    UserScript
    0.65
     "");
    0.65
    AccessorTable
    0.64
     "")
    0.63
    Activations Density 0.984%

    No Known Activations