© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1584
    Prev
    Next
    INDEX
    Explanations

    words related to scientific or legal findings or procedures

    oai_token-act-pair · gemini-2.0-flash

    actions or experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    styleType
    -0.61
     الرياضيه
    -0.58
    <bos>
    -0.57
    Datuak
    -0.57
     analysed
    -0.57
    onAttach
    -0.57
     presentarse
    -0.55
     uLocal
    -0.53
     MotionEvent
    -0.53
    OCCURRED
    -0.52
    POSITIVE LOGITS
    ISupport
    0.54
    ặng
    0.49
    allage
    0.47
     hab
    0.47
    Carry
    0.47
    MIDDLEWARE
    0.46
    равда
    0.45
    orance
    0.45
     SqlConnection
    0.44
    umns
    0.44
    Activations Density 4.950%

    No Known Activations