© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11849
    Prev
    Next
    INDEX
    Explanations

    parts of code, specifically Go code, including variable declarations, functions calls related to HTTP requests, and string formatting

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ")->
    -0.64
    __':
    -0.62
    __":
    -0.60
     незавершена
    -0.59
    ])->
    -0.58
    stylers
    -0.56
    -//
    -0.54
    ⓧ
    -0.54
    '])->
    -0.54
    gdx
    -0.53
    POSITIVE LOGITS
     Empfang
    0.64
    FXMLLoader
    0.60
    solete
    0.59
     Volkes
    0.56
    rophi
    0.56
     Irrelevant
    0.56
     Chop
    0.55
    requestCode
    0.55
     Cataly
    0.54
    hrung
    0.54
    Activations Density 0.973%

    No Known Activations