© 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. 11338
    Prev
    Next
    INDEX
    Explanations

    terms related to financial reimbursement, legal claims, and technical interpolation

    oai_token-act-pair · gemini-2.0-flash

    compensation

    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
    ney
    -0.91
    NEY
    -0.81
    aj
    -0.73
    ANE
    -0.66
    ane
    -0.65
     Compensation
    -0.61
    caris
    -0.60
     compensation
    -0.59
    NullCheck
    -0.59
    }],
    -0.59
    POSITIVE LOGITS
    Sucesor
    0.65
    artifactId
    0.64
    QMetaType
    0.61
    :✨
    0.61
    marshaller
    0.56
    Etymology
    0.54
    UIControlState
    0.53
    <bos>
    0.53
    horabuena
    0.53
    greenrobot
    0.52
    Activations Density 3.623%

    No Known Activations