© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11260
    Prev
    Next
    INDEX
    Explanations

    instances of failure affecting policies, procedures, systems, or entities

    oai_token-act-pair · gemini-2.0-flash

    fail

    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
     fail
    -1.32
    fail
    -1.23
     Fail
    -1.20
     fails
    -1.02
     виправивши
    -0.98
    ScopeManager
    -0.97
    parsedMessage
    -0.94
    Fail
    -0.93
     Fails
    -0.92
     FAIL
    -0.91
    POSITIVE LOGITS
    <bos>
    0.53
     recently
    0.48
     already
    0.43
    '
    0.43
     May
    0.43
     planned
    0.42
     debut
    0.42
     tričko
    0.42
     debuts
    0.42
    的には
    0.42
    Activations Density 1.297%

    No Known Activations